text-generationstable
alfred
A robust conversational model designed to be used for both chat and instruct use cases.
- vendor
- LightOn · Alfred
- sizes
- 40b
- ollama
ollama pull alfred
ailicense unknown
model/alfredv1.0.0ollama.com/library
Mo · class model
Models 283
Reference data about AI models: who made them, what they are for, published sizes, and a providers list with the exact id and command a runtime needs. Every entry links to its provider page.
283 of 283 shown
embeddingstable
all-minilm
Embedding models on very large sentence level datasets.
- vendor
- sentence-transformers · MiniLM
- sizes
- 22m 33m
- ollama
ollama pull all-minilm
model/all-minilmv1.0.0ollama.com/library
text-generationstable
athene-v2
Athene-V2 is a 72B parameter model which excels at code completion, mathematics, and log extraction tasks.
- vendor
- Nexusflow · Athene
- sizes
- 72b
- ollama
ollama pull athene-v2
model/athene-v2v1.0.0ollama.com/library
text-to-speechstable
Aura 1
Context-aware text-to-speech model applying natural pacing and expressiveness.
- vendor
- Deepgram · Aura
model/aura-1v1.0.0model-atoms.com
text-to-speechstable
Aura 2 EN
Context-aware English text-to-speech model that applies natural pacing, expressiveness, and fillers based on context.
- vendor
- Deepgram · Aura 2
model/aura-2-env1.0.0model-atoms.com
text-to-speechstable
Aura 2 ES
Context-aware Spanish text-to-speech model that applies natural pacing, expressiveness, and fillers based on context.
- vendor
- Deepgram · Aura 2
model/aura-2-esv1.0.0model-atoms.com
text-generationstable
aya
Aya 23, released by Cohere, is a new family of state-of-the-art, multilingual models that support 23 languages.
- vendor
- Cohere · Aya
- sizes
- 8b 35b
- ollama
ollama pull aya
ailicense unknown
model/ayav1.0.0ollama.com/library
text-generationstable
aya-expanse
Cohere For AI's language models trained to perform well across 23 different languages.
- vendor
- Cohere · Aya
- sizes
- 8b 32b
- ollama
ollama pull aya-expanse
model/aya-expansev1.0.0ollama.com/library
multimodalstable
bakllava
BakLLaVA is a multimodal model consisting of the Mistral 7B base model augmented with the LLaVA architecture.
- vendor
- SkunkworksAI · BakLLaVA
- sizes
- 7b
- ollama
ollama pull bakllava
model/bakllavav1.0.0ollama.com/library
text-generationstable
bespoke-minicheck
A state-of-the-art fact-checking model developed by Bespoke Labs.
- vendor
- Bespoke Labs · Bespoke
- sizes
- 7b
- ollama
ollama pull bespoke-minicheck
ailicense unknown
model/bespoke-minicheckv1.0.0ollama.com/library
otherstable
BGE Base EN v1.5
General embedding base model transforming text into 768-dimensional vectors.
- vendor
- BAAI · BGE
model/bge-base-en-v1.5v1.0.0model-atoms.com
otherstable
BGE Large EN v1.5
General embedding large model transforming text into 1024-dimensional vectors.
- vendor
- BAAI · BGE
model/bge-large-en-v1.5v1.0.0model-atoms.com
otherstable
BGE Reranker Base
Reranker model that takes question and document as input and outputs a relevance similarity score.
- vendor
- BAAI · BGE
ailicense unknown
model/bge-reranker-basev1.0.0model-atoms.com
otherstable
BGE Small EN v1.5
General embedding small model transforming text into 384-dimensional vectors.
- vendor
- BAAI · BGE
model/bge-small-en-v1.5v1.0.0model-atoms.com
embeddingstable
bge-large
Embedding model from BAAI mapping texts to vectors.
- vendor
- BAAI · BGE
- sizes
- 335m
- ollama
ollama pull bge-large
model/bge-largev1.0.0ollama.com/library
embeddingstable
bge-m3
BGE-M3 is a new model from BAAI distinguished for its versatility in Multi-Functionality, Multi-Linguality, and Multi-Granularity.
- vendor
- BAAI · BGE
- sizes
- 567m
- ollama
ollama pull bge-m3
model/bge-m3v1.1.0ollama.com/library
code-generationstable
codebooga
A high-performing code instruct model created by merging two existing code models.
- vendor
- oobabooga · CodeBooga
- sizes
- 34b
- ollama
ollama pull codebooga
ailicense unknown
model/codeboogav1.0.0ollama.com/library
code-generationstable
codegeex4
A versatile model for AI software development scenarios, including code completion.
- vendor
- Zhipu AI · CodeGeeX
- sizes
- 9b
- ollama
ollama pull codegeex4
ailicense unknown
model/codegeex4v1.0.0ollama.com/library
code-generationstable
codegemma
CodeGemma is a collection of powerful, lightweight models that can perform a variety of coding tasks like fill-in-the-middle code completion, code generation, natural language understanding, mathematical reasoning, and instruction following.
- vendor
- Google · Gemma
- sizes
- 2b 7b
- ollama
ollama pull codegemma
ailicense unknown
model/codegemmav1.0.0ollama.com/library
code-generationstable
codellama
A large language model that can use text prompts to generate and discuss code.
- vendor
- Meta · Code Llama
- sizes
- 7b 13b 34b 70b
- ollama
ollama pull codellama
ailicense unknown
model/codellamav1.0.0ollama.com/library
code-generationstable
codeqwen
CodeQwen1.5 is a large language model pretrained on a large amount of code data.
- vendor
- Alibaba · Qwen
- sizes
- 7b
- ollama
ollama pull codeqwen
ailicense unknown
model/codeqwenv1.0.0ollama.com/library
code-generationstable
codestral
Codestral is Mistral AI’s first-ever code model designed for code generation tasks.
- vendor
- Mistral AI · Codestral
- sizes
- 22b
- ollama
ollama pull codestral
ailicense unknown
model/codestralv1.0.0ollama.com/library
code-generationstable
codeup
Great code generation model based on Llama2.
- vendor
- DeepSE · CodeUp
- sizes
- 13b
- ollama
ollama pull codeup
ailicense unknown
model/codeupv1.0.0ollama.com/library
text-generationstable
cogito
Cogito v1 Preview is a family of hybrid reasoning models by Deep Cogito that outperform the best available open models of the same size, including counterparts from LLaMA, DeepSeek, and Qwen across most standard benchmarks.
- vendor
- Deep Cogito · Cogito
- sizes
- 3b 8b 14b 32b 70b
- ollama
ollama pull cogito
model/cogitov1.0.0ollama.com/library
text-generationstable
cogito-2.1
The Cogito v2.1 LLMs are instruction tuned generative models. All models are released under MIT license for commercial use.
- vendor
- Deep Cogito · Cogito
- sizes
- 671b
- ollama
ollama pull cogito-2.1
ailicense unknown
model/cogito-2.1v1.0.0ollama.com/library
text-generationstable
command-a
111 billion parameter model optimized for demanding enterprises that require fast, secure, and high-quality AI
- vendor
- Cohere · Command
- sizes
- 111b
- ollama
ollama pull command-a
model/command-av1.0.0ollama.com/library
text-generationstable
command-r
Command R is a Large Language Model optimized for conversational interaction and long context tasks.
- vendor
- Cohere · Command
- sizes
- 35b
- ollama
ollama pull command-r
model/command-rv1.0.0ollama.com/library
text-generationstable
command-r-plus
Command R+ is a powerful, scalable large language model purpose-built to excel at real-world enterprise use cases.
- vendor
- Cohere · Command
- sizes
- 104b
- ollama
ollama pull command-r-plus
model/command-r-plusv1.0.0ollama.com/library
text-generationstable
command-r7b
The smallest model in Cohere's R series delivers top-tier speed, efficiency, and quality to build powerful AI applications on commodity GPUs and edge devices.
- vendor
- Cohere · Command
- sizes
- 7b
- ollama
ollama pull command-r7b
model/command-r7bv1.0.0ollama.com/library
text-generationstable
command-r7b-arabic
A new state-of-the-art version of the lightweight Command R7B model that excels in advanced Arabic language capabilities for enterprises in the Middle East and Northern Africa.
- vendor
- Cohere · Command
- sizes
- 7b
- ollama
ollama pull command-r7b-arabic
model/command-r7b-arabicv1.0.0ollama.com/library
text-generationstable
dbrx
DBRX is an open, general-purpose LLM created by Databricks.
- vendor
- Databricks · DBRX
- sizes
- 132b
- ollama
ollama pull dbrx
ailicense unknown
model/dbrxv1.0.0ollama.com/library
code-generationstable
deepcoder
DeepCoder is a fully open-Source 14B coder model at O3-mini level, with a 1.5B version also available.
- vendor
- Agentica · DeepCoder
- sizes
- 1.5b 14b
- ollama
ollama pull deepcoder
ailicense unknown
model/deepcoderv1.0.0ollama.com/library
text-generationstable
deepscaler
A fine-tuned version of Deepseek-R1-Distilled-Qwen-1.5B that surpasses the performance of OpenAI’s o1-preview with just 1.5B parameters on popular math evaluations.
- vendor
- Agentica · DeepScaleR
- sizes
- 1.5b
- ollama
ollama pull deepscaler
ailicense unknown
model/deepscalerv1.0.0ollama.com/library
text-generationstable
DeepSeek R1 Distill Qwen 32B
Distilled from DeepSeek-R1 based on Qwen2.5; outperforms OpenAI o1-mini on several benchmarks.
- vendor
- DeepSeek · DeepSeek R1
model/deepseek-r1-distill-qwen-32bv1.0.0model-atoms.com
code-generationstable
deepseek-coder
DeepSeek Coder is a capable coding model trained on two trillion code and natural language tokens.
- vendor
- DeepSeek · DeepSeek Coder
- sizes
- 1.3b 6.7b 33b
- ollama
ollama pull deepseek-coder
ailicense unknown
model/deepseek-coderv1.0.0ollama.com/library
code-generationstable
deepseek-coder-v2
An open-source Mixture-of-Experts code language model that achieves performance comparable to GPT4-Turbo in code-specific tasks.
- vendor
- DeepSeek · DeepSeek Coder
- sizes
- 16b 236b
- ollama
ollama pull deepseek-coder-v2
ailicense unknown
model/deepseek-coder-v2v1.0.0ollama.com/library
text-generationstable
deepseek-llm
An advanced language model crafted with 2 trillion bilingual tokens.
- vendor
- DeepSeek · DeepSeek
- sizes
- 7b 67b
- ollama
ollama pull deepseek-llm
ailicense unknown
model/deepseek-llmv1.0.0ollama.com/library
multimodalstable
deepseek-ocr
DeepSeek-OCR is a vision-language model that can perform token-efficient OCR.
- vendor
- DeepSeek · DeepSeek
- sizes
- 3b
- ollama
ollama pull deepseek-ocr
model/deepseek-ocrv1.0.0ollama.com/library
reasoningstable
deepseek-r1
DeepSeek-R1 is a family of open reasoning models with performance approaching that of leading models, such as O3 and Gemini 2.5 Pro.
- vendor
- DeepSeek · DeepSeek-R1
- sizes
- 1.5b 7b 8b 14b 32b 70b 671b
- ollama
ollama pull deepseek-r1
model/deepseek-r1v1.0.0ollama.com/library
text-generationstable
deepseek-v2
A strong, economical, and efficient Mixture-of-Experts language model.
- vendor
- DeepSeek · DeepSeek-V
- sizes
- 16b 236b
- ollama
ollama pull deepseek-v2
ailicense unknown
model/deepseek-v2v1.0.0ollama.com/library
text-generationstable
deepseek-v2.5
An upgraded version of DeekSeek-V2 that integrates the general and coding abilities of both DeepSeek-V2-Chat and DeepSeek-Coder-V2-Instruct.
- vendor
- DeepSeek · DeepSeek-V
- sizes
- 236b
- ollama
ollama pull deepseek-v2.5
ailicense unknown
model/deepseek-v2.5v1.0.0ollama.com/library
text-generationstable
deepseek-v3
A strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token.
- vendor
- DeepSeek · DeepSeek-V
- sizes
- 671b
- ollama
ollama pull deepseek-v3
ailicense unknown
model/deepseek-v3v1.0.0ollama.com/library
reasoningstable
deepseek-v3.1
DeepSeek-V3.1-Terminus is a hybrid model that supports both thinking mode and non-thinking mode.
- vendor
- DeepSeek · DeepSeek-V
- sizes
- 671b
- ollama
ollama pull deepseek-v3.1
model/deepseek-v3.1v1.0.0ollama.com/library
reasoningstable
deepseek-v4-flash
DeepSeek-V4-Flash is a preview of the DeepSeek-V4 series, a Mixture-of-Experts model with 284B total parameters and 13B activated, built for efficient reasoning across a 1M-token context window.
- vendor
- DeepSeek · DeepSeek-V
- ollama
ollama pull deepseek-v4-flash
model/deepseek-v4-flashv1.0.0ollama.com/library
reasoningstable
deepseek-v4-pro
DeepSeek-V4-Pro is a frontier Mixture-of-Experts model with a large context window and three reasoning modes.
- vendor
- DeepSeek · DeepSeek-V
- ollama
ollama pull deepseek-v4-pro
model/deepseek-v4-prov1.0.0ollama.com/library
visionstable
DETR ResNet-50
DETection TRansformer model trained end-to-end on COCO 2017 object detection dataset (118k annotated images).
- vendor
- Meta · DETR
ailicense unknown
model/detr-resnet-50v1.0.0model-atoms.com
code-generationstable
devstral
Devstral: the best open source model for coding agents
- vendor
- Mistral AI · Devstral
- sizes
- 24b
- ollama
ollama pull devstral
model/devstralv1.0.0ollama.com/library
code-generationstable
devstral-2
123B model that excels at using tools to explore codebases, editing multiple files and power software engineering agents.
- vendor
- Mistral AI · Devstral
- sizes
- 123b
- ollama
ollama pull devstral-2
model/devstral-2v1.0.0ollama.com/library
code-generationstable
devstral-small-2
24B model that excels at using tools to explore codebases, editing multiple files and power software engineering agents.
- vendor
- Mistral AI · Devstral
- sizes
- 24b
- ollama
ollama pull devstral-small-2
model/devstral-small-2v1.0.0ollama.com/library
otherstable
DistilBERT SST-2 INT8
Distilled BERT model fine-tuned on SST-2 for sentiment classification.
- vendor
- HuggingFace · DistilBERT
ailicense unknown
model/distilbert-sst-2-int8v1.0.0model-atoms.com
text-generationstable
dolphin-llama3
Dolphin 2.9 is a new model with 8B and 70B sizes by Eric Hartford based on Llama 3 that has a variety of instruction, conversational, and coding skills.
- vendor
- Cognitive Computations · Dolphin
- sizes
- 8b 70b
- ollama
ollama pull dolphin-llama3
ailicense unknown
model/dolphin-llama3v1.0.0ollama.com/library
text-generationstable
dolphin-mistral
The uncensored Dolphin model based on Mistral that excels at coding tasks. Updated to version 2.8.
- vendor
- Cognitive Computations · Dolphin
- sizes
- 7b
- ollama
ollama pull dolphin-mistral
ailicense unknown
model/dolphin-mistralv1.0.0ollama.com/library
text-generationstable
dolphin-mixtral
Uncensored, 8x7b and 8x22b fine-tuned models based on the Mixtral mixture of experts models that excels at coding tasks. Created by Eric Hartford.
- vendor
- Cognitive Computations · Dolphin
- sizes
- 8x7b 8x22b
- ollama
ollama pull dolphin-mixtral
ailicense unknown
model/dolphin-mixtralv1.0.0ollama.com/library
text-generationstable
dolphin-phi
2.7B uncensored Dolphin model by Eric Hartford, based on the Phi language model by Microsoft Research.
- vendor
- Cognitive Computations · Dolphin
- sizes
- 2.7b
- ollama
ollama pull dolphin-phi
ailicense unknown
model/dolphin-phiv1.0.0ollama.com/library
text-generationstable
dolphin3
Dolphin 3.0 Llama 3.1 8B 🐬 is the next generation of the Dolphin series of instruct-tuned models designed to be the ultimate general purpose local model, enabling coding, math, agentic, function calling, and general use cases.
- vendor
- Cognitive Computations · Dolphin
- sizes
- 8b
- ollama
ollama pull dolphin3
ailicense unknown
model/dolphin3v1.0.0ollama.com/library
code-generationstable
dolphincoder
A 7B and 15B uncensored variant of the Dolphin model family that excels at coding, based on StarCoder2.
- vendor
- Cognitive Computations · Dolphin
- sizes
- 7b 15b
- ollama
ollama pull dolphincoder
ailicense unknown
model/dolphincoderv1.0.0ollama.com/library
otherstable
DreamShaper 8 LCM
Stable Diffusion model fine-tuned to be better at photorealism.
- vendor
- Lykon · DreamShaper
ailicense unknown
model/dreamshaper-8-lcmv1.0.0model-atoms.com
code-generationstable
duckdb-nsql
7B parameter text-to-SQL model made by MotherDuck and Numbers Station.
- vendor
- MotherDuck · DuckDB-NSQL
- sizes
- 7b
- ollama
ollama pull duckdb-nsql
ailicense unknown
model/duckdb-nsqlv1.0.0ollama.com/library
embeddingstable
embeddinggemma
EmbeddingGemma is a 300M parameter embedding model from Google.
- vendor
- Google · Gemma
- sizes
- 300m
- ollama
ollama pull embeddinggemma
model/embeddinggemmav1.1.0ollama.com/library
text-generationstable
everythinglm
Uncensored Llama2 based model with support for a 16K context window.
- vendor
- Totally Not An LLM · EverythingLM
- sizes
- 13b
- ollama
ollama pull everythinglm
ailicense unknown
model/everythinglmv1.0.0ollama.com/library
text-generationstable
exaone-deep
EXAONE Deep exhibits superior capabilities in various reasoning tasks including math and coding benchmarks, ranging from 2.4B to 32B parameters developed and released by LG AI Research.
- vendor
- LG AI Research · EXAONE
- sizes
- 2.4b 7.8b 32b
- ollama
ollama pull exaone-deep
ailicense unknown
model/exaone-deepv1.0.0ollama.com/library
text-generationstable
exaone3.5
EXAONE 3.5 is a collection of instruction-tuned bilingual (English and Korean) generative models ranging from 2.4B to 32B parameters, developed and released by LG AI Research.
- vendor
- LG AI Research · EXAONE
- sizes
- 2.4b 7.8b 32b
- ollama
ollama pull exaone3.5
ailicense unknown
model/exaone3.5v1.0.0ollama.com/library
text-generationstable
falcon
A large language model built by the Technology Innovation Institute (TII) for use in summarization, text generation, and chat bots.
- vendor
- TII · Falcon
- sizes
- 7b 40b 180b
- ollama
ollama pull falcon
ailicense unknown
model/falconv1.0.0ollama.com/library
text-generationstable
falcon2
Falcon2 is an 11B parameters causal decoder-only model built by TII and trained over 5T tokens.
- vendor
- TII · Falcon
- sizes
- 11b
- ollama
ollama pull falcon2
ailicense unknown
model/falcon2v1.0.0ollama.com/library
text-generationstable
falcon3
A family of efficient AI models under 10B parameters performant in science, math, and coding through innovative training techniques.
- vendor
- TII · Falcon
- sizes
- 1b 3b 7b 10b
- ollama
ollama pull falcon3
ailicense unknown
model/falcon3v1.0.0ollama.com/library
text-generationstable
firefunction-v2
An open weights function calling model based on Llama 3, competitive with GPT-4o function calling capabilities.
- vendor
- Fireworks AI · FireFunction
- sizes
- 70b
- ollama
ollama pull firefunction-v2
model/firefunction-v2v1.0.0ollama.com/library
otherstable
FLUX 1 Schnell
12 billion parameter rectified flow transformer capable of generating images from text descriptions.
- vendor
- Black Forest Labs · FLUX 1
ailicense unknown
model/flux-1-schnellv1.0.0model-atoms.com
otherstable
FLUX 2 Dev
Image model capable of generating highly realistic and detailed images with multi-reference support.
- vendor
- Black Forest Labs · FLUX 2
ailicense unknown
model/flux-2-devv1.0.0model-atoms.com
otherstable
FLUX 2 Klein 4B
Ultra-fast distilled image model delivering state-of-the-art quality for interactive workflows and real-time previews.
- vendor
- Black Forest Labs · FLUX 2
ailicense unknown
model/flux-2-klein-4bv1.0.0model-atoms.com
otherstable
FLUX 2 Klein 9B
Ultra-fast distilled image model with enhanced quality; unifies image generation and editing in a single model.
- vendor
- Black Forest Labs · FLUX 2
ailicense unknown
model/flux-2-klein-9bv1.0.0model-atoms.com
otherstable
Flux ASR
First conversational speech recognition model built specifically for voice agents.
- vendor
- Deepgram · Flux ASR
model/fluxv1.0.0model-atoms.com
text-generationstable
functiongemma
FunctionGemma is a specialized version of Google's Gemma 3 270M model fine-tuned explicitly for function calling.
- vendor
- Google · Gemma
- sizes
- 270m
- ollama
ollama pull functiongemma
model/functiongemmav1.0.0ollama.com/library
text-generationstable
gemma
Gemma is a family of lightweight, state-of-the-art open models built by Google DeepMind. Updated to version 1.1
- vendor
- Google · Gemma
- sizes
- 2b 7b
- ollama
ollama pull gemma
ailicense unknown
model/gemmav1.1.0ollama.com/library
text-generationstable
Gemma SEA-LION v4 27B IT
Southeast Asian Languages In One Network — LLMs pretrained and instruct-tuned for the Southeast Asia region.
- vendor
- AI Singapore · SEA-LION
ailicense unknown
model/gemma-sea-lion-v4-27b-itv1.0.0model-atoms.com
text-generationstable
gemma2
Google Gemma 2 is a high-performing and efficient model available in three sizes: 2B, 9B, and 27B.
- vendor
- Google · Gemma 2
- sizes
- 2b 9b 27b
- ollama
ollama pull gemma2
ailicense unknown
model/gemma2v1.0.0ollama.com/library
multimodalstable
gemma3
The current, most capable model that runs on a single GPU.
- vendor
- Google · Gemma 3
- sizes
- 270m 1b 4b 12b 27b
- ollama
ollama pull gemma3
model/gemma3v1.1.0ollama.com/library
text-generationstable
gemma3n
Gemma 3n models are designed for efficient execution on everyday devices such as laptops, tablets or phones.
- vendor
- Google · Gemma 3n
- sizes
- 2b 4b
- ollama
ollama pull gemma3n
ailicense unknown
model/gemma3nv1.0.0ollama.com/library
reasoningstable
gemma4
Gemma 4 models are designed to deliver frontier-level performance at each size. They are well-suited for reasoning, agentic workflows, coding, and multimodal understanding.
- vendor
- Google · Gemma
- sizes
- 2b 4b 12b 26b 31b
- ollama
ollama pull gemma4
model/gemma4v1.1.0ollama.com/library
reasoningstable
glm-4.7-flash
As the strongest model in the 30B class, GLM-4.7-Flash offers a new option for lightweight deployment that balances performance and efficiency.
- vendor
- Zhipu AI · GLM-4
- ollama
ollama pull glm-4.7-flash
model/glm-4.7-flashv1.1.0ollama.com/library
reasoningstable
glm-5.1
GLM-5.1 is our next-generation flagship model for agentic engineering, with significantly stronger coding capabilities than its predecessor. It achieves state-of-the-art performance on SWE-Bench Pro and leads GLM-5 by a wide margin.
- vendor
- Zhipu AI · GLM-5
- ollama
ollama pull glm-5.1
model/glm-5.1v1.0.0ollama.com/library
reasoningstable
glm-5.2
GLM-5.2 is Z.ai’s flagship model for the era of long-horizon tasks.
- vendor
- Zhipu AI · GLM-5
- ollama
ollama pull glm-5.2
model/glm-5.2v1.0.0ollama.com/library
reasoningstable
glm-5.3
Z.ai's flagship model and the most capable open-weights model for coding, with major gains on long-horizon agentic tasks.
- vendor
- Zhipu AI · GLM-5
- ollama
ollama pull glm-5.3
model/glm-5.3v1.0.0ollama.com/library
reasoningstable
glm-5.3-flash
Z.ai's first natively multimodal model, approaching Claude Opus 4.8 on coding and agentic benchmarks with just 18B active parameters.
- vendor
- Zhipu AI · GLM-5
- ollama
ollama pull glm-5.3-flash
model/glm-5.3-flashv1.0.0ollama.com/library
multimodalstable
glm-ocr
GLM-OCR is a multimodal OCR model for complex document understanding, built on the GLM-V encoder–decoder architecture.
- vendor
- Zhipu AI · GLM
- ollama
ollama pull glm-ocr
model/glm-ocrv1.0.0ollama.com/library
text-generationstable
glm4
A strong multi-lingual general language model with competitive performance to Llama 3.
- vendor
- Zhipu AI · GLM
- sizes
- 9b
- ollama
ollama pull glm4
ailicense unknown
model/glm4v1.0.0ollama.com/library
text-generationstable
goliath
A language model created by combining two fine-tuned Llama 2 70B models into one.
- vendor
- Alpin · Goliath
- ollama
ollama pull goliath
ailicense unknown
model/goliathv1.0.0ollama.com/library
reasoningstable
gpt-oss
OpenAI’s open-weight models designed for powerful reasoning, agentic tasks, and versatile developer use cases.
- vendor
- OpenAI · GPT-OSS
- sizes
- 20b 120b
- ollama
ollama pull gpt-oss
model/gpt-ossv1.1.0ollama.com/library
reasoningstable
gpt-oss-safeguard
gpt-oss-safeguard-20b and gpt-oss-safeguard-120b are safety reasoning models built-upon gpt-oss
- vendor
- OpenAI · GPT-OSS
- sizes
- 20b 120b
- ollama
ollama pull gpt-oss-safeguard
model/gpt-oss-safeguardv1.0.0ollama.com/library
text-generationstable
Granite 4.0 H Micro
Industry-leading results in agentic tasks including instruction following and function calling; suited for RAG, multi-agent workflows, and edge deployments.
- vendor
- IBM · Granite 4.0
model/granite-4.0-h-microv1.0.0model-atoms.com
code-generationstable
granite-code
A family of open foundation models by IBM for Code Intelligence
- vendor
- IBM · Granite
- sizes
- 3b 8b 20b 34b
- ollama
ollama pull granite-code
ailicense unknown
model/granite-codev1.0.0ollama.com/library
embeddingstable
granite-embedding
The IBM Granite Embedding 30M and 278M models models are text-only dense biencoder embedding models, with 30M available in English only and 278M serving multilingual use cases.
- vendor
- IBM · Granite
- sizes
- 30m 278m
- ollama
ollama pull granite-embedding
model/granite-embeddingv1.0.0ollama.com/library
text-generationstable
granite3-dense
The IBM Granite 2B and 8B models are designed to support tool-based use cases and support for retrieval augmented generation (RAG), streamlining code generation, translation and bug fixing.
- vendor
- IBM · Granite
- sizes
- 2b 8b
- ollama
ollama pull granite3-dense
model/granite3-densev1.0.0ollama.com/library
text-generationstable
granite3-guardian
The IBM Granite Guardian 3.0 2B and 8B models are designed to detect risks in prompts and/or responses.
- vendor
- IBM · Granite
- sizes
- 2b 8b
- ollama
ollama pull granite3-guardian
ailicense unknown
model/granite3-guardianv1.0.0ollama.com/library
text-generationstable
granite3-moe
The IBM Granite 1B and 3B models are the first mixture of experts (MoE) Granite models from IBM designed for low latency usage.
- vendor
- IBM · Granite
- sizes
- 1b 3b
- ollama
ollama pull granite3-moe
model/granite3-moev1.0.0ollama.com/library
text-generationstable
granite3.1-dense
The IBM Granite 2B and 8B models are text-only dense LLMs trained on over 12 trillion tokens of data, demonstrated significant improvements over their predecessors in performance and speed in IBM’s initial testing.
- vendor
- IBM · Granite
- sizes
- 2b 8b
- ollama
ollama pull granite3.1-dense
model/granite3.1-densev1.0.0ollama.com/library
text-generationstable
granite3.1-moe
The IBM Granite 1B and 3B models are long-context mixture of experts (MoE) Granite models from IBM designed for low latency usage.
- vendor
- IBM · Granite
- sizes
- 1b 3b
- ollama
ollama pull granite3.1-moe
model/granite3.1-moev1.0.0ollama.com/library
text-generationstable
granite3.2
Granite-3.2 is a family of long-context AI models from IBM Granite fine-tuned for thinking capabilities.
- vendor
- IBM · Granite
- sizes
- 2b 8b
- ollama
ollama pull granite3.2
model/granite3.2v1.0.0ollama.com/library
multimodalstable
granite3.2-vision
A compact and efficient vision-language model, specifically designed for visual document understanding, enabling automated content extraction from tables, charts, infographics, plots, diagrams, and more.
- vendor
- IBM · Granite
- sizes
- 2b
- ollama
ollama pull granite3.2-vision
model/granite3.2-visionv1.0.0ollama.com/library
text-generationstable
granite3.3
IBM Granite 2B and 8B models are 128K context length language models that have been fine-tuned for improved reasoning and instruction-following capabilities.
- vendor
- IBM · Granite
- sizes
- 2b 8b
- ollama
ollama pull granite3.3
model/granite3.3v1.0.0ollama.com/library
text-generationstable
granite4
Granite 4 features improved instruction following (IF) and tool-calling capabilities, making them more effective in enterprise applications.
- vendor
- IBM · Granite
- sizes
- 350m 1b 3b
- ollama
ollama pull granite4
model/granite4v1.0.0ollama.com/library
text-generationstable
granite4.1
IBM Granite Models are a family of enterprise-ready, open foundation models that support multilingual capabilities, coding, retrieval-augmented generation (RAG), tool use, and structured JSON output. Released under Apache 2.0 license.
- vendor
- IBM · Granite
- sizes
- 3b 8b 30b
- ollama
ollama pull granite4.1
model/granite4.1v1.0.0ollama.com/library
reasoningstable
granite4.1-guardian
Granite Guardian 4.1 is a specialized safety and judging model from IBM Research that evaluates whether LLM prompts and responses meet specified harm criteria.
- vendor
- IBM · Granite
- sizes
- 8b
- ollama
ollama pull granite4.1-guardian
model/granite4.1-guardianv1.0.0ollama.com/library
text-generationstable
granite4.2
IBM Granite Models are a family of enterprise-ready, open foundation models that support multilingual capabilities, coding, retrieval-augmented generation (RAG), tool use, thinking and structured JSON output. Released under Apache 2.0 license.
- vendor
- IBM · Granite
- sizes
- 3b 8b 30b
- ollama
ollama pull granite4.2
ailicense unknown
model/granite4.2v1.0.0ollama.com/library
text-generationstable
Hermes 2 Pro Mistral 7B
Upgraded, retrained version of Nous Hermes 2 with function calling and JSON mode capabilities.
- vendor
- Nous Research · Hermes 2
model/hermes-2-pro-mistral-7bv1.0.0model-atoms.com
text-generationstable
hermes3
Hermes 3 is the latest version of the flagship Hermes series of LLMs by Nous Research
- vendor
- Nous Research · Hermes
- sizes
- 3b 8b 70b 405b
- ollama
ollama pull hermes3
model/hermes3v1.0.0ollama.com/library
translationstable
IndicTrans2 EN-Indic 1B
First open-source transformer-based multilingual NMT model supporting high-quality translation across all 22 scheduled Indic languages.
- vendor
- AI4Bharat · IndicTrans2
ailicense unknown
model/indictrans2-en-indic-1bv1.0.0model-atoms.com
text-generationstable
internlm2
InternLM2.5 is a 7B parameter model tailored for practical scenarios with outstanding reasoning capability.
- vendor
- Shanghai AI Lab · InternLM
- sizes
- 1m 1.8b 7b 20b
- ollama
ollama pull internlm2
ailicense unknown
model/internlm2v1.0.0ollama.com/library
text-generationstable
Kimi K2.5
Frontier-scale open-source model with a 256k context window.
- vendor
- Moonshot AI · Kimi K2
model/kimi-k2.5v1.0.0model-atoms.com
reasoningstable
kimi-k2.6
Kimi K2.6 is an open-source, native multimodal agentic model that advances practical capabilities in long-horizon coding, coding-driven design, proactive autonomous execution, and swarm-based task orchestration.
- vendor
- Moonshot AI · Kimi
- ollama
ollama pull kimi-k2.6
model/kimi-k2.6v1.1.0ollama.com/library
code-generationstable
kimi-k2.7-code
Kimi K2.7 Code is Moonshot AI's coding-focused agentic model built upon Kimi K2.6, with substantial improvements on real-world long-horizon coding tasks and roughly 30% lower thinking-token usage.
- vendor
- Moonshot AI · Kimi
- ollama
ollama pull kimi-k2.7-code
model/kimi-k2.7-codev1.0.0ollama.com/library
reasoningstable
kimi-k3
Kimi K3 is an open-weight, native multimodal agentic model and our most capable model to date.
- vendor
- Moonshot AI · Kimi
- ollama
ollama pull kimi-k3
model/kimi-k3v1.0.0ollama.com/library
reasoningstable
laguna-s-2.1
Our most capable model to date, designed for long-horizon work. 70.2% on Terminal-Bench 2.1 at 118B-A8B.
- vendor
- unknown
- ollama
ollama pull laguna-s-2.1
model/laguna-s-2.1v1.0.0ollama.com/library
reasoningstable
laguna-xs-2.1
Laguna XS 2.1 is a 33B total parameter Mixture-of-Experts model with 3B activated parameters per token designed for agentic coding and long-horizon work on a local machine.
- vendor
- unknown
- ollama
ollama pull laguna-xs-2.1
model/laguna-xs-2.1v1.0.0ollama.com/library
reasoningstable
laguna-xs.2
Laguna XS.2 is a 33B total parameter Mixture-of-Experts model with 3B activated parameters per token designed for agentic coding and long-horizon work on a local machine.
- vendor
- unknown
- ollama
ollama pull laguna-xs.2
model/laguna-xs.2v1.0.0ollama.com/library
text-generationstable
lfm2
LFM2 is a family of hybrid models designed for on-device deployment. LFM2-24B-A2B is the largest model in the family, scaling the architecture to 24 billion parameters while keeping inference efficient.
- vendor
- Liquid AI · LFM
- sizes
- 24b
- ollama
ollama pull lfm2
model/lfm2v1.0.0ollama.com/library
reasoningstable
lfm2.5
LFM2.5-8B-A1B, an edge model built for fast, reliable tool calling on consumer hardware.
- vendor
- Liquid AI · LFM
- sizes
- 8b
- ollama
ollama pull lfm2.5
model/lfm2.5v1.0.0ollama.com/library
reasoningstable
lfm2.5-thinking
LFM2.5 is a new family of hybrid models designed for on-device deployment.
- vendor
- Liquid AI · LFM
- sizes
- 1.2b
- ollama
ollama pull lfm2.5-thinking
model/lfm2.5-thinkingv1.0.0ollama.com/library
text-generationstable
Llama 4 Scout 17B 16E Instruct
17 billion parameter natively multimodal model with 16 experts (mixture-of-experts architecture).
- vendor
- Meta · Llama 4
model/llama-4-scout-17b-16e-instructv1.0.0model-atoms.com
text-generationstable
llama-guard3
Llama Guard 3 is a series of models fine-tuned for content safety classification of LLM inputs and responses.
- vendor
- Meta · Llama Guard
- sizes
- 1b 8b
- ollama
ollama pull llama-guard3
ailicense unknown
model/llama-guard3v1.1.0ollama.com/library
text-generationstable
llama-pro
An expansion of Llama 2 that specializes in integrating both general language understanding and domain-specific knowledge, particularly in programming and mathematics.
- vendor
- Tencent ARC · LLaMA Pro
- ollama
ollama pull llama-pro
ailicense unknown
model/llama-prov1.0.0ollama.com/library
text-generationstable
llama2
Llama 2 is a collection of foundation language models ranging from 7B to 70B parameters.
- vendor
- Meta · Llama 2
- sizes
- 7b 13b 70b
- ollama
ollama pull llama2
ailicense unknown
model/llama2v1.1.0ollama.com/library
text-generationstable
llama2-chinese
Llama 2 based model fine tuned to improve Chinese dialogue ability.
- vendor
- Meta · Llama 2
- sizes
- 7b 13b
- ollama
ollama pull llama2-chinese
ailicense unknown
model/llama2-chinesev1.0.0ollama.com/library
text-generationstable
llama2-uncensored
Uncensored Llama 2 model by George Sung and Jarrad Hope.
- vendor
- Meta · Llama 2
- sizes
- 7b 70b
- ollama
ollama pull llama2-uncensored
ailicense unknown
model/llama2-uncensoredv1.0.0ollama.com/library
text-generationstable
llama3
Meta Llama 3: The most capable openly available LLM to date
- vendor
- Meta · Llama 3
- sizes
- 8b 70b
- ollama
ollama pull llama3
ailicense unknown
model/llama3v1.1.0ollama.com/library
text-generationstable
llama3-chatqa
A model from NVIDIA based on Llama 3 that excels at conversational question answering (QA) and retrieval-augmented generation (RAG).
- vendor
- Meta · Llama 3
- sizes
- 8b 70b
- ollama
ollama pull llama3-chatqa
ailicense unknown
model/llama3-chatqav1.0.0ollama.com/library
text-generationstable
llama3-gradient
This model extends LLama-3 8B's context length from 8k to over 1m tokens.
- vendor
- Meta · Llama 3
- sizes
- 8b 70b
- ollama
ollama pull llama3-gradient
ailicense unknown
model/llama3-gradientv1.0.0ollama.com/library
text-generationstable
llama3-groq-tool-use
A series of models from Groq that represent a significant advancement in open-source AI capabilities for tool use/function calling.
- vendor
- Meta · Llama 3
- sizes
- 8b 70b
- ollama
ollama pull llama3-groq-tool-use
model/llama3-groq-tool-usev1.0.0ollama.com/library
text-generationstable
llama3.1
Llama 3.1 is a new state-of-the-art model from Meta available in 8B, 70B and 405B parameter sizes.
- vendor
- Meta · Llama 3
- sizes
- 8b 70b 405b
- ollama
ollama pull llama3.1
model/llama3.1v1.1.0ollama.com/library
text-generationstable
llama3.2
Meta's Llama 3.2 goes small with 1B and 3B models.
- vendor
- Meta · Llama 3
- sizes
- 1b 3b
- ollama
ollama pull llama3.2
model/llama3.2v1.1.0ollama.com/library
multimodalstable
llama3.2-vision
Llama 3.2 Vision is a collection of instruction-tuned image reasoning generative models in 11B and 90B sizes.
- vendor
- Meta · Llama 3
- sizes
- 11b 90b
- ollama
ollama pull llama3.2-vision
model/llama3.2-visionv1.1.0ollama.com/library
text-generationstable
llama3.3
New state of the art 70B model. Llama 3.3 70B offers similar performance compared to the Llama 3.1 405B model.
- vendor
- Meta · Llama 3
- sizes
- 70b
- ollama
ollama pull llama3.3
model/llama3.3v1.1.0ollama.com/library
multimodalstable
llama4
Meta's latest collection of multimodal models.
- vendor
- Meta · Llama 4
- sizes
- 16x17b 128x17b
- ollama
ollama pull llama4
model/llama4v1.0.0ollama.com/library
multimodalstable
llava
🌋 LLaVA is a novel end-to-end trained large multimodal model that combines a vision encoder and Vicuna for general-purpose visual and language understanding. Updated to version 1.6.
- vendor
- LLaVA · LLaVA
- sizes
- 7b 13b 34b
- ollama
ollama pull llava
model/llavav1.0.0ollama.com/library
multimodalstable
LLaVA 1.5 7B HF
Open-source multimodal chatbot trained by fine-tuning LLaMA/Vicuna on visual instruction data; supports image captioning and visual question answering.
- vendor
- LLaVA · LLaVA 1.5
model/llava-1.5-7b-hfv1.0.0model-atoms.com
multimodalstable
llava-llama3
A LLaVA model fine-tuned from Llama 3 Instruct with better scores in several benchmarks.
- vendor
- LLaVA · LLaVA
- sizes
- 8b
- ollama
ollama pull llava-llama3
model/llava-llama3v1.0.0ollama.com/library
multimodalstable
llava-phi3
A new small LLaVA model fine-tuned from Phi 3 Mini.
- vendor
- LLaVA · LLaVA
- sizes
- 3.8b
- ollama
ollama pull llava-phi3
model/llava-phi3v1.0.0ollama.com/library
otherstable
Lucid Origin
Most adaptable and prompt-responsive model with strengths in sharp graphic design, full-HD renders, and accurate text rendering.
- vendor
- Leonardo · Lucid
ailicense unknown
model/lucid-originv1.0.0model-atoms.com
translationstable
M2M-100 1.2B
Multilingual encoder-decoder model trained for many-to-many multilingual translation.
- vendor
- Meta · M2M-100
model/m2m100-1.2bv1.0.0model-atoms.com
code-generationstable
magicoder
🎩 Magicoder is a family of 7B parameter models trained on 75K synthetic instruction data using OSS-Instruct, a novel approach to enlightening LLMs with open-source code snippets.
- vendor
- iSE Lab · Magicoder
- sizes
- 7b
- ollama
ollama pull magicoder
ailicense unknown
model/magicoderv1.0.0ollama.com/library
reasoningstable
magistral
Magistral is a small, efficient reasoning model with 24B parameters.
- vendor
- Mistral AI · Magistral
- sizes
- 24b
- ollama
ollama pull magistral
model/magistralv1.0.0ollama.com/library
text-generationstable
marco-o1
An open large reasoning model for real-world solutions by the Alibaba International Digital Commerce Group (AIDC-AI).
- vendor
- Alibaba · Marco
- sizes
- 7b
- ollama
ollama pull marco-o1
ailicense unknown
model/marco-o1v1.0.0ollama.com/library
text-generationstable
mathstral
MathΣtral: a 7B model designed for math reasoning and scientific discovery by Mistral AI.
- vendor
- Mistral AI · Mathstral
- sizes
- 7b
- ollama
ollama pull mathstral
ailicense unknown
model/mathstralv1.0.0ollama.com/library
multimodalstable
medgemma
MedGemma is a collection of Gemma 3 variants that are trained for performance on medical text and image comprehension.
- vendor
- Google · MedGemma
- sizes
- 4b 27b
- ollama
ollama pull medgemma
model/medgemmav1.0.0ollama.com/library
multimodalstable
medgemma1.5
MedGemma 1.5 4B is an updated version of the MedGemma 4B model.
- vendor
- Google · MedGemma
- sizes
- 4b
- ollama
ollama pull medgemma1.5
model/medgemma1.5v1.0.0ollama.com/library
text-generationstable
meditron
Open-source medical large language model adapted from Llama 2 to the medical domain.
- vendor
- EPFL · Meditron
- sizes
- 7b 70b
- ollama
ollama pull meditron
ailicense unknown
model/meditronv1.0.0ollama.com/library
text-generationstable
medllama2
Fine-tuned Llama 2 model to answer medical questions based on an open source medical dataset.
- vendor
- Siraj Raval · MedLlama
- sizes
- 7b
- ollama
ollama pull medllama2
ailicense unknown
model/medllama2v1.0.0ollama.com/library
text-generationstable
megadolphin
MegaDolphin-2.2-120b is a transformation of Dolphin-2.2-70b created by interleaving the model with itself.
- vendor
- Cognitive Computations · Dolphin
- sizes
- 120b
- ollama
ollama pull megadolphin
ailicense unknown
model/megadolphinv1.0.0ollama.com/library
text-to-speechstable
MeloTTS
High-quality multi-lingual text-to-speech library.
- vendor
- MyShell · MeloTTS
ailicense unknown
model/melottsv1.0.0model-atoms.com
multimodalstable
minicpm-v
A series of multimodal LLMs (MLLMs) designed for vision-language understanding.
- vendor
- OpenBMB · MiniCPM-V
- sizes
- 8b
- ollama
ollama pull minicpm-v
model/minicpm-vv1.0.1ollama.com/library
multimodalstable
minicpm-v4.5
A GPT-4o Level MLLM for Single Image, Multi Image and High-FPS Video Understanding on Your Phone
- vendor
- OpenBMB · MiniCPM-V
- sizes
- 8b
- ollama
ollama pull minicpm-v4.5
model/minicpm-v4.5v1.0.1ollama.com/library
multimodalstable
minicpm-v4.6
A Pocket-Sized MLLM for Ultra-Efficient Image and Video Understanding on Your Phone
- vendor
- OpenBMB · MiniCPM-V
- sizes
- 1b
- ollama
ollama pull minicpm-v4.6
model/minicpm-v4.6v1.0.1ollama.com/library
reasoningstable
minimax-m2.7
MiniMax's M2-series model for coding, agentic workflows, and professional productivity.
- vendor
- MiniMax · MiniMax
- ollama
ollama pull minimax-m2.7
model/minimax-m2.7v1.0.0ollama.com/library
reasoningstable
minimax-m3
MiniMax M3: Coding & Agentic Frontier. 1M context window. Native Multimodality.
- vendor
- MiniMax · MiniMax
- ollama
ollama pull minimax-m3
model/minimax-m3v1.0.0ollama.com/library
multimodalstable
ministral-3
The Ministral 3 family is designed for edge deployment, capable of running on a wide range of hardware.
- vendor
- Mistral AI · Ministral
- sizes
- 3b 8b 14b
- ollama
ollama pull ministral-3
model/ministral-3v1.0.0ollama.com/library
text-generationstable
mistral
The 7B model released by Mistral AI, updated to version 0.3.
- vendor
- Mistral AI · Mistral
- sizes
- 7b
- ollama
ollama pull mistral
model/mistralv1.0.0ollama.com/library
text-generationstable
Mistral 7B Instruct v0.1
Instruct fine-tuned version of the Mistral-7B model.
- vendor
- MistralAI · Mistral 7B
model/mistral-7b-instruct-v0.1v1.0.0model-atoms.com
text-generationstable
Mistral 7B Instruct v0.2
32k context window instruct model with updated rope-theta and no sliding-window attention.
- vendor
- MistralAI · Mistral 7B
model/mistral-7b-instruct-v0.2v1.0.0model-atoms.com
text-generationstable
Mistral 7B Instruct v0.2 LoRA
Mistral 7B instruct v0.2 dedicated for inference with LoRA adapters.
- vendor
- MistralAI · Mistral 7B
model/mistral-7b-instruct-v0.2-lorav1.0.0model-atoms.com
text-generationstable
mistral-large
Mistral Large 2 is Mistral's new flagship model that is significantly more capable in code generation, mathematics, and reasoning with 128k context window and support for dozens of languages.
- vendor
- Mistral AI · Mistral Large
- sizes
- 123b
- ollama
ollama pull mistral-large
model/mistral-largev1.0.0ollama.com/library
multimodalstable
mistral-large-3
A general-purpose multimodal mixture-of-experts model for production-grade tasks and enterprise workloads.
- vendor
- Mistral AI · Mistral Large
- ollama
ollama pull mistral-large-3
model/mistral-large-3v1.0.0ollama.com/library
reasoningstable
mistral-medium-3.5
Mistral Medium 3.5 is the first flagship model of Mistral AI that merged instruction-following, reasoning, and coding in a single set of 128B weights.
- vendor
- Mistral AI · Mistral
- sizes
- 128b
- ollama
ollama pull mistral-medium-3.5
model/mistral-medium-3.5v1.0.0ollama.com/library
text-generationstable
mistral-nemo
A state-of-the-art 12B model with 128k context length, built by Mistral AI in collaboration with NVIDIA.
- vendor
- Mistral AI · Mistral NeMo
- sizes
- 12b
- ollama
ollama pull mistral-nemo
model/mistral-nemov1.0.0ollama.com/library
text-generationstable
mistral-openorca
Mistral OpenOrca is a 7 billion parameter model, fine-tuned on top of the Mistral 7B model using the OpenOrca dataset.
- vendor
- Open-Orca · Mistral OpenOrca
- sizes
- 7b
- ollama
ollama pull mistral-openorca
ailicense unknown
model/mistral-openorcav1.0.0ollama.com/library
text-generationstable
mistral-small
Mistral Small 3 sets a new benchmark in the “small” Large Language Models category below 70B.
- vendor
- Mistral AI · Mistral Small
- sizes
- 22b 24b
- ollama
ollama pull mistral-small
model/mistral-smallv1.0.0ollama.com/library
multimodalstable
mistral-small3.1
Building upon Mistral Small 3, Mistral Small 3.1 (2503) adds state-of-the-art vision understanding and enhances long context capabilities up to 128k tokens without compromising text performance.
- vendor
- Mistral AI · Mistral Small
- sizes
- 24b
- ollama
ollama pull mistral-small3.1
model/mistral-small3.1v1.1.0ollama.com/library
multimodalstable
mistral-small3.2
An update to Mistral Small that improves on function calling, instruction following, and less repetition errors.
- vendor
- Mistral AI · Mistral Small
- sizes
- 24b
- ollama
ollama pull mistral-small3.2
model/mistral-small3.2v1.0.0ollama.com/library
text-generationstable
mistrallite
MistralLite is a fine-tuned model based on Mistral with enhanced capabilities of processing long contexts.
- vendor
- Amazon · MistralLite
- sizes
- 7b
- ollama
ollama pull mistrallite
ailicense unknown
model/mistrallitev1.0.0ollama.com/library
text-generationstable
mixtral
A set of Mixture of Experts (MoE) model with open weights by Mistral AI in 8x7b and 8x22b parameter sizes.
- vendor
- Mistral AI · Mixtral
- sizes
- 8x7b 8x22b
- ollama
ollama pull mixtral
model/mixtralv1.0.0ollama.com/library
multimodalstable
moondream
moondream2 is a small vision language model designed to run efficiently on edge devices.
- vendor
- vikhyat · Moondream
- sizes
- 1.8b
- ollama
ollama pull moondream
model/moondreamv1.0.0ollama.com/library
reasoningstable
muse-glimmer
Meta's latest open model built for always-on local agents. 30B parameters, licensed under Apache 2.0 and runs on a single GPU — tuned for tool use, long tasks, and failure recovery.
- vendor
- Meta · Muse
- sizes
- 30b
- ollama
ollama pull muse-glimmer
model/muse-glimmerv1.0.1ollama.com/library
embeddingstable
mxbai-embed-large
State-of-the-art large embedding model from mixedbread.ai
- vendor
- Mixedbread · mxbai
- sizes
- 335m
- ollama
ollama pull mxbai-embed-large
model/mxbai-embed-largev1.0.0ollama.com/library
text-generationstable
nemotron
Llama-3.1-Nemotron-70B-Instruct is a large language model customized by NVIDIA to improve the helpfulness of LLM generated responses to user queries.
- vendor
- NVIDIA · Nemotron
- sizes
- 70b
- ollama
ollama pull nemotron
model/nemotronv1.0.0ollama.com/library
reasoningstable
nemotron-3-nano
Nemotron-3-Nano is a new Standard for Efficient, Open, and Intelligent Agentic Models, now updated with a 4B parameter count model.
- vendor
- NVIDIA · Nemotron 3
- sizes
- 4b 30b
- ollama
ollama pull nemotron-3-nano
model/nemotron-3-nanov1.0.0ollama.com/library
reasoningstable
nemotron-3-super
NVIDIA Nemotron 3 Super is a 120B open MoE model activating just 12B parameters to deliver maximum compute efficiency and accuracy for complex multi-agent applications.
- vendor
- NVIDIA · Nemotron 3
- sizes
- 120b
- ollama
ollama pull nemotron-3-super
model/nemotron-3-superv1.0.0ollama.com/library
reasoningstable
nemotron-3-ultra
NVIDIA Nemotron 3 Ultra is built for high-throughput reasoning and long-running agent workflows.
- vendor
- NVIDIA · Nemotron 3
- ollama
ollama pull nemotron-3-ultra
model/nemotron-3-ultrav1.0.0ollama.com/library
reasoningstable
nemotron-3.5-lightning
NVIDIA Nemotron 3.5 Lightning is an open 30B mixture-of-experts (MoE) model with 3B active parameters built for always-on agents.
- vendor
- NVIDIA · Nemotron 3
- sizes
- 30b
- ollama
ollama pull nemotron-3.5-lightning
model/nemotron-3.5-lightningv1.0.0ollama.com/library
reasoningstable
nemotron-cascade-2
An open 30B MoE model from NVIDIA with 3B activated parameters that delivers strong reasoning and agentic capabilities.
- vendor
- NVIDIA · Nemotron
- sizes
- 30b
- ollama
ollama pull nemotron-cascade-2
model/nemotron-cascade-2v1.0.0ollama.com/library
text-generationstable
nemotron-mini
A commercial-friendly small language model by NVIDIA optimized for roleplay, RAG QA, and function calling.
- vendor
- NVIDIA · Nemotron
- sizes
- 4b
- ollama
ollama pull nemotron-mini
model/nemotron-miniv1.0.0ollama.com/library
reasoningstable
nemotron3
NVIDIA Nemotron 3 Nano Omni is a multimodal large language model that unifies video, audio, image, and text understanding to support enterprise-grade Q&A, summarization, transcription, and document intelligence workflows.
- vendor
- NVIDIA · Nemotron
- sizes
- 33b
- ollama
ollama pull nemotron3
model/nemotron3v1.1.0ollama.com/library
text-generationstable
neural-chat
A fine-tuned model based on Mistral with good coverage of domain and language.
- vendor
- Intel · Neural Chat
- sizes
- 7b
- ollama
ollama pull neural-chat
ailicense unknown
model/neural-chatv1.0.0ollama.com/library
text-generationstable
nexusraven
Nexus Raven is a 13B instruction tuned model for function calling tasks.
- vendor
- Nexusflow · NexusRaven
- sizes
- 13b
- ollama
ollama pull nexusraven
ailicense unknown
model/nexusravenv1.0.0ollama.com/library
embeddingstable
nomic-embed-text
A high-performing open embedding model with a large token context window.
- vendor
- Nomic AI · Nomic Embed
- ollama
ollama pull nomic-embed-text
model/nomic-embed-textv1.0.0ollama.com/library
embeddingstable
nomic-embed-text-v2-moe
nomic-embed-text-v2-moe is a multilingual MoE text embedding model that excels at multilingual retrieval.
- vendor
- Nomic AI · Nomic Embed
- ollama
ollama pull nomic-embed-text-v2-moe
model/nomic-embed-text-v2-moev1.0.0ollama.com/library
code-generationstable
north-mini-code-1.0
North Mini Code is Cohere's first model for developers — a 30B Mixture-of-Experts model with 3B active parameters, built for agentic software engineering.
- vendor
- Cohere · North
- ollama
ollama pull north-mini-code-1.0
model/north-mini-code-1.0v1.0.1ollama.com/library
text-generationstable
notus
A 7B chat model fine-tuned with high-quality data and based on Zephyr.
- vendor
- Argilla · Notus
- sizes
- 7b
- ollama
ollama pull notus
ailicense unknown
model/notusv1.0.0ollama.com/library
text-generationstable
notux
A top-performing mixture of experts model, fine-tuned with high-quality data.
- vendor
- Argilla · Notux
- sizes
- 8x7b
- ollama
ollama pull notux
ailicense unknown
model/notuxv1.0.0ollama.com/library
text-generationstable
nous-hermes
General use models based on Llama and Llama 2 from Nous Research.
- vendor
- Nous Research · Hermes
- sizes
- 7b 13b
- ollama
ollama pull nous-hermes
ailicense unknown
model/nous-hermesv1.0.0ollama.com/library
text-generationstable
nous-hermes2
The powerful family of models by Nous Research that excels at scientific discussion and coding tasks.
- vendor
- Nous Research · Hermes
- sizes
- 10.7b 34b
- ollama
ollama pull nous-hermes2
ailicense unknown
model/nous-hermes2v1.0.0ollama.com/library
text-generationstable
nous-hermes2-mixtral
The Nous Hermes 2 model from Nous Research, now trained over Mixtral.
- vendor
- Nous Research · Hermes
- sizes
- 8x7b
- ollama
ollama pull nous-hermes2-mixtral
ailicense unknown
model/nous-hermes2-mixtralv1.0.0ollama.com/library
otherstable
Nova 3
Deepgram speech-to-text model for transcribing audio.
- vendor
- Deepgram · Nova
model/nova-3v1.0.0model-atoms.com
code-generationstable
nuextract
A 3.8B model fine-tuned on a private high-quality synthetic dataset for information extraction, based on Phi-3.
- vendor
- NuMind · NuExtract
- sizes
- 3.8b
- ollama
ollama pull nuextract
ailicense unknown
model/nuextractv1.0.0ollama.com/library
reasoningstable
olmo-3
Olmo is a series of Open language models designed to enable the science of language models. These models are pre-trained on the Dolma 3 dataset and post-trained on the Dolci datasets.
- vendor
- AI2 · OLMo
- sizes
- 7b 32b
- ollama
ollama pull olmo-3
model/olmo-3v1.0.0ollama.com/library
reasoningstable
olmo-3.1
Olmo is a series of Open language models designed to enable the science of language models. These models are pre-trained on the Dolma 3 dataset and post-trained on the Dolci datasets.
- vendor
- AI2 · OLMo
- sizes
- 32b
- ollama
ollama pull olmo-3.1
model/olmo-3.1v1.0.0ollama.com/library
text-generationstable
olmo2
OLMo 2 is a new family of 7B and 13B models trained on up to 5T tokens. These models are on par with or better than equivalently sized fully open models, and competitive with open-weight models such as Llama 3.1 on English academic benchmarks.
- vendor
- AI2 · OLMo
- sizes
- 7b 13b
- ollama
ollama pull olmo2
ailicense unknown
model/olmo2v1.0.0ollama.com/library
text-generationstable
open-orca-platypus2
Merge of the Open Orca OpenChat model and the Garage-bAInd Platypus 2 model. Designed for chat and code generation.
- vendor
- Open-Orca · OpenOrca
- sizes
- 13b
- ollama
ollama pull open-orca-platypus2
ailicense unknown
model/open-orca-platypus2v1.0.0ollama.com/library
text-generationstable
openchat
A family of open-source models trained on a wide variety of data, surpassing ChatGPT on various benchmarks. Updated to version 3.5-0106.
- vendor
- OpenChat · OpenChat
- sizes
- 7b
- ollama
ollama pull openchat
ailicense unknown
model/openchatv1.0.0ollama.com/library
code-generationstable
opencoder
OpenCoder is an open and reproducible code LLM family which includes 1.5B and 8B models, supporting chat in English and Chinese languages.
- vendor
- OpenCoder · OpenCoder
- sizes
- 1.5b 8b
- ollama
ollama pull opencoder
ailicense unknown
model/opencoderv1.0.0ollama.com/library
text-generationstable
openhermes
OpenHermes 2.5 is a 7B model fine-tuned by Teknium on Mistral with fully open datasets.
- vendor
- Nous Research · Hermes
- ollama
ollama pull openhermes
ailicense unknown
model/openhermesv1.0.0ollama.com/library
reasoningstable
openthinker
A fully open-source family of reasoning models built using a dataset derived by distilling DeepSeek-R1.
- vendor
- Open Thoughts · OpenThinker
- sizes
- 7b 32b
- ollama
ollama pull openthinker
ailicense unknown
model/openthinkerv1.0.0ollama.com/library
text-generationstable
orca-mini
A general-purpose model ranging from 3 billion parameters to 70 billion, suitable for entry-level hardware.
- vendor
- Pankaj Mathur · Orca Mini
- sizes
- 3b 7b 13b 70b
- ollama
ollama pull orca-mini
ailicense unknown
model/orca-miniv1.0.0ollama.com/library
text-generationstable
orca2
Orca 2 is built by Microsoft research, and are a fine-tuned version of Meta's Llama 2 models. The model is designed to excel particularly in reasoning.
- vendor
- Microsoft · Orca
- sizes
- 7b 13b
- ollama
ollama pull orca2
ailicense unknown
model/orca2v1.0.0ollama.com/library
text-generationstable
ornith
A self-improving family of open-source models for agentic coding
- vendor
- unknown
- sizes
- 9b 35b
- ollama
ollama pull ornith
model/ornithv1.0.0ollama.com/library
multimodalstable
ornith-1.5
Chirp Chirp! 🐦 We are introducing Ornith-1.5, a major step toward building foundation models through end-to-end self-improvement.
- vendor
- unknown
- sizes
- 9b 35b 397b
- ollama
ollama pull ornith-1.5
model/ornith-1.5v1.0.0ollama.com/library
embeddingstable
paraphrase-multilingual
Sentence-transformers model that can be used for tasks like clustering or semantic search.
- vendor
- sentence-transformers · MiniLM
- sizes
- 278m
- ollama
ollama pull paraphrase-multilingual
model/paraphrase-multilingualv1.0.0ollama.com/library
text-generationstable
phi
Phi-2: a 2.7B language model by Microsoft Research that demonstrates outstanding reasoning and language understanding capabilities.
- vendor
- Microsoft · Phi
- sizes
- 2.7b
- ollama
ollama pull phi
ailicense unknown
model/phiv1.0.0ollama.com/library
text-generationstable
Phi-2
Transformer-based model with next-word prediction objective, trained on 1.4T tokens from web and synthetic sources.
- vendor
- Microsoft · Phi
ailicense unknown
model/phi-2v1.0.0model-atoms.com
text-generationstable
phi3
Phi-3 is a family of lightweight 3B (Mini) and 14B (Medium) state-of-the-art open models by Microsoft.
- vendor
- Microsoft · Phi-3
- sizes
- 3.8b 14b
- ollama
ollama pull phi3
ailicense unknown
model/phi3v1.0.0ollama.com/library
text-generationstable
phi3.5
A lightweight AI model with 3.8 billion parameters with performance overtaking similarly and larger sized models.
- vendor
- Microsoft · Phi-3
- sizes
- 3.8b
- ollama
ollama pull phi3.5
ailicense unknown
model/phi3.5v1.0.0ollama.com/library
text-generationstable
phi4
Phi-4 is a 14B parameter, state-of-the-art open model from Microsoft.
- vendor
- Microsoft · Phi-4
- sizes
- 14b
- ollama
ollama pull phi4
ailicense unknown
model/phi4v1.0.0ollama.com/library
text-generationstable
phi4-mini
Phi-4-mini brings significant enhancements in multilingual support, reasoning, and mathematics, and now, the long-awaited function calling feature is finally supported.
- vendor
- Microsoft · Phi-4
- sizes
- 3.8b
- ollama
ollama pull phi4-mini
model/phi4-miniv1.0.0ollama.com/library
reasoningstable
phi4-mini-reasoning
Phi 4 mini reasoning is a lightweight open model that balances efficiency with advanced reasoning ability.
- vendor
- Microsoft · Phi-4
- sizes
- 3.8b
- ollama
ollama pull phi4-mini-reasoning
ailicense unknown
model/phi4-mini-reasoningv1.0.0ollama.com/library
reasoningstable
phi4-reasoning
Phi 4 reasoning and reasoning plus are 14-billion parameter open-weight reasoning models that rival much larger models on complex reasoning tasks.
- vendor
- Microsoft · Phi-4
- sizes
- 14b
- ollama
ollama pull phi4-reasoning
ailicense unknown
model/phi4-reasoningv1.0.0ollama.com/library
code-generationstable
phind-codellama
Code generation model based on Code Llama.
- vendor
- Phind · Phind CodeLlama
- sizes
- 34b
- ollama
ollama pull phind-codellama
ailicense unknown
model/phind-codellamav1.0.0ollama.com/library
otherstable
Phoenix 1.0
Generates images with exceptional prompt adherence and coherent text rendering.
- vendor
- Leonardo · Phoenix
ailicense unknown
model/phoenix-1.0v1.0.0model-atoms.com
otherstable
PLaMo Embedding 1B
Japanese text embedding model that converts Japanese text input into numerical vectors for information retrieval, text classification, and clustering.
- vendor
- Preferred Networks · PLaMo Embedding
ailicense unknown
model/plamo-embedding-1bv1.0.0model-atoms.com
text-generationstable
qwen
Qwen 1.5 is a series of large language models by Alibaba Cloud spanning from 0.5B to 110B parameters
- vendor
- Alibaba · Qwen
- sizes
- 0.5b 1.8b 4b 7b 14b 32b 72b 110b
- ollama
ollama pull qwen
ailicense unknown
model/qwenv1.0.0ollama.com/library
text-generationstable
qwen2
Qwen2 is a new series of large language models from Alibaba group
- vendor
- Alibaba · Qwen2
- sizes
- 0.5b 1.5b 7b 72b
- ollama
ollama pull qwen2
model/qwen2v1.0.0ollama.com/library
text-generationstable
qwen2-math
Qwen2 Math is a series of specialized math language models built upon the Qwen2 LLMs, which significantly outperforms the mathematical capabilities of open-source models and even closed-source models (e.g., GPT4o).
- vendor
- Alibaba · Qwen2
- sizes
- 1.5b 7b 72b
- ollama
ollama pull qwen2-math
ailicense unknown
model/qwen2-mathv1.0.0ollama.com/library
text-generationstable
qwen2.5
Qwen2.5 models are pretrained on Alibaba's latest large-scale dataset, encompassing up to 18 trillion tokens. The model supports up to 128K tokens and has multilingual support.
- vendor
- Alibaba · Qwen2.5
- sizes
- 0.5b 1.5b 3b 7b 14b 32b 72b
- ollama
ollama pull qwen2.5
model/qwen2.5v1.0.0ollama.com/library
code-generationstable
qwen2.5-coder
The latest series of Code-Specific Qwen models, with significant improvements in code generation, code reasoning, and code fixing.
- vendor
- Alibaba · Qwen2.5-Coder
- sizes
- 0.5b 1.5b 3b 7b 14b 32b
- ollama
ollama pull qwen2.5-coder
model/qwen2.5-coderv1.1.0ollama.com/library
multimodalstable
qwen2.5vl
Flagship vision-language model of Qwen and also a significant leap from the previous Qwen2-VL.
- vendor
- Alibaba · Qwen2.5
- sizes
- 3b 7b 32b 72b
- ollama
ollama pull qwen2.5vl
model/qwen2.5vlv1.0.0ollama.com/library
reasoningstable
qwen3
Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models.
- vendor
- Alibaba · Qwen3
- sizes
- 0.6b 1.7b 4b 8b 14b 30b 32b 235b
- ollama
ollama pull qwen3
model/qwen3v1.1.0ollama.com/library
code-generationstable
qwen3-coder
Alibaba's performant long context models for agentic and coding tasks.
- vendor
- Alibaba · Qwen3-Coder
- sizes
- 30b 480b
- ollama
ollama pull qwen3-coder
model/qwen3-coderv1.0.0ollama.com/library
code-generationstable
qwen3-coder-next
Qwen3-Coder-Next is a coding-focused language model from Alibaba's Qwen team, optimized for agentic coding workflows and local development.
- vendor
- Alibaba · Qwen3-Coder
- ollama
ollama pull qwen3-coder-next
model/qwen3-coder-nextv1.0.0ollama.com/library
embeddingstable
qwen3-embedding
Building upon the foundational models of the Qwen3 series, Qwen3 Embedding provides a comprehensive range of text embeddings models in various sizes
- vendor
- Alibaba · Qwen3-Embedding
- sizes
- 0.6b 4b 8b
- ollama
ollama pull qwen3-embedding
model/qwen3-embeddingv1.1.0ollama.com/library
reasoningstable
qwen3-next
The first installment in the Qwen3-Next series with strong performance in terms of both parameter efficiency and inference speed.
- vendor
- Alibaba · Qwen3
- sizes
- 80b
- ollama
ollama pull qwen3-next
model/qwen3-nextv1.0.0ollama.com/library
reasoningstable
qwen3-vl
The most powerful vision-language model in the Qwen model family to date.
- vendor
- Alibaba · Qwen3-VL
- sizes
- 2b 4b 8b 30b 32b 235b
- ollama
ollama pull qwen3-vl
model/qwen3-vlv1.0.0ollama.com/library
reasoningstable
qwen3.5
Qwen 3.5 is a family of open-source multimodal models that delivers exceptional utility and performance.
- vendor
- Alibaba · Qwen3
- sizes
- 0.8b 2b 4b 9b 27b 35b 122b
- ollama
ollama pull qwen3.5
model/qwen3.5v1.0.0ollama.com/library
reasoningstable
qwen3.6
Qwen3.6 delivers substantial upgrades in agentic coding and thinking preservation than previous Qwen models.
- vendor
- Alibaba · Qwen3
- sizes
- 27b 35b
- ollama
ollama pull qwen3.6
model/qwen3.6v1.0.0ollama.com/library
reasoningstable
qwen3.8
Qwen3.8 delivers substantial gains across coding, professional work, research, and long-horizon agentic tasks.
- vendor
- Alibaba · Qwen3
- sizes
- 27b
- ollama
ollama pull qwen3.8
model/qwen3.8v1.0.0ollama.com/library
reasoningstable
qwen3.8-flash-next
This experimental preview of the architecture that will underpin Qwen4.
- vendor
- Alibaba · Qwen3
- ollama
ollama pull qwen3.8-flash-next
model/qwen3.8-flash-nextv1.0.0ollama.com/library
reasoningstable
qwq
QwQ is the reasoning model of the Qwen series.
- vendor
- Alibaba · QwQ
- sizes
- 32b
- ollama
ollama pull qwq
model/qwqv1.1.0ollama.com/library
reasoningstable
r1-1776
A version of the DeepSeek-R1 model that has been post trained to provide unbiased, accurate, and factual information by Perplexity.
- vendor
- Perplexity · R1-1776
- sizes
- 70b 671b
- ollama
ollama pull r1-1776
ailicense unknown
model/r1-1776v1.0.0ollama.com/library
text-generationstable
reader-lm
A series of models that convert HTML content to Markdown content, which is useful for content conversion tasks.
- vendor
- Jina AI · Reader-LM
- sizes
- 0.5b 1.5b
- ollama
ollama pull reader-lm
ailicense unknown
model/reader-lmv1.0.0ollama.com/library
text-generationstable
reflection
A high-performing model trained with a new technique called Reflection-tuning that teaches a LLM to detect mistakes in its reasoning and correct course.
- vendor
- Matt Shumer · Reflection
- sizes
- 70b
- ollama
ollama pull reflection
ailicense unknown
model/reflectionv1.0.0ollama.com/library
visionstable
ResNet-50
50 layers deep image classification CNN trained on more than 1 million images from the ImageNet dataset.
- vendor
- Microsoft · ResNet
ailicense unknown
model/resnet-50v1.0.0model-atoms.com
text-generationstable
rnj-1
Rnj-1 is a family of 8B parameter open-weight, dense models trained from scratch by Essential AI, optimized for code and STEM with capabilities on par with SOTA open-weight models.
- vendor
- Essential AI · Rnj
- sizes
- 8b
- ollama
ollama pull rnj-1
model/rnj-1v1.0.1ollama.com/library
text-generationstable
sailor2
Sailor2 are multilingual language models made for South-East Asia. Available in 1B, 8B, and 20B parameter sizes.
- vendor
- SEA AI Lab · Sailor
- sizes
- 1b 8b 20b
- ollama
ollama pull sailor2
ailicense unknown
model/sailor2v1.0.0ollama.com/library
text-generationstable
samantha-mistral
A companion assistant trained in philosophy, psychology, and personal relationships. Based on Mistral.
- vendor
- Cognitive Computations · Samantha
- sizes
- 7b
- ollama
ollama pull samantha-mistral
ailicense unknown
model/samantha-mistralv1.0.0ollama.com/library
text-generationstable
shieldgemma
ShieldGemma is set of instruction tuned models for evaluating the safety of text prompt input and text output responses against a set of defined safety policies.
- vendor
- Google · ShieldGemma
- sizes
- 2b 9b 27b
- ollama
ollama pull shieldgemma
ailicense unknown
model/shieldgemmav1.0.0ollama.com/library
reasoningstable
smallthinker
A new small reasoning model fine-tuned from the Qwen 2.5 3B Instruct model.
- vendor
- PowerInfer · SmallThinker
- sizes
- 3b
- ollama
ollama pull smallthinker
ailicense unknown
model/smallthinkerv1.0.0ollama.com/library
otherstable
SmartTurn v2
Open source community-driven native audio turn detection model in its second version.
- vendor
- Pipecat · SmartTurn
model/smart-turn-v2v1.0.0model-atoms.com
text-generationstable
smollm
🪐 A family of small models with 135M, 360M, and 1.7B parameters, trained on a new high-quality dataset.
- vendor
- Hugging Face · SmolLM
- sizes
- 135m 360m 1.7b
- ollama
ollama pull smollm
ailicense unknown
model/smollmv1.0.0ollama.com/library
text-generationstable
smollm2
SmolLM2 is a family of compact language models available in three size: 135M, 360M, and 1.7B parameters.
- vendor
- Hugging Face · SmolLM
- sizes
- 135m 360m 1.7b
- ollama
ollama pull smollm2
model/smollm2v1.0.0ollama.com/library
embeddingstable
snowflake-arctic-embed
A suite of text embedding models by Snowflake, optimized for performance.
- vendor
- Snowflake · Arctic Embed
- sizes
- 22m 33m 110m 137m 335m
- ollama
ollama pull snowflake-arctic-embed
model/snowflake-arctic-embedv1.0.0ollama.com/library
embeddingstable
snowflake-arctic-embed2
Snowflake's frontier embedding model. Arctic Embed 2.0 adds multilingual support without sacrificing English performance or scalability.
- vendor
- Snowflake · Arctic Embed
- sizes
- 568m
- ollama
ollama pull snowflake-arctic-embed2
model/snowflake-arctic-embed2v1.0.0ollama.com/library
text-generationstable
solar
A compact, yet powerful 10.7B large language model designed for single-turn conversation.
- vendor
- Upstage · Solar
- sizes
- 10.7b
- ollama
ollama pull solar
ailicense unknown
model/solarv1.0.0ollama.com/library
text-generationstable
solar-pro
Solar Pro Preview: an advanced large language model (LLM) with 22 billion parameters designed to fit into a single GPU
- vendor
- Upstage · Solar
- sizes
- 22b
- ollama
ollama pull solar-pro
ailicense unknown
model/solar-prov1.0.0ollama.com/library
code-generationstable
sqlcoder
SQLCoder is a code completion model fined-tuned on StarCoder for SQL generation tasks
- vendor
- Defog · SQLCoder
- sizes
- 7b 15b
- ollama
ollama pull sqlcoder
ailicense unknown
model/sqlcoderv1.0.0ollama.com/library
text-generationstable
SQLCoder 7B 2
SQL-specialized model designed to help non-technical users understand and query data in SQL databases.
- vendor
- Defog · SQLCoder
ailicense unknown
model/sqlcoder-7b-2v1.0.0model-atoms.com
otherstable
Stable Diffusion v1.5 Img2Img
Generate a new image from an input image using Stable Diffusion.
- vendor
- RunwayML · Stable Diffusion v1.5
ailicense unknown
model/stable-diffusion-v1-5-img2imgv1.0.0model-atoms.com
otherstable
Stable Diffusion v1.5 Inpainting
Stable Diffusion model with inpainting capability using a mask to selectively edit image regions.
- vendor
- RunwayML · Stable Diffusion v1.5
ailicense unknown
model/stable-diffusion-v1-5-inpaintingv1.0.0model-atoms.com
otherstable
Stable Diffusion XL Base 1.0
Diffusion-based text-to-image model that generates and modifies images based on text prompts.
- vendor
- Stability AI · Stable Diffusion XL
ailicense unknown
model/stable-diffusion-xl-base-1.0v1.0.0model-atoms.com
otherstable
Stable Diffusion XL Lightning
Lightning-fast text-to-image generation model capable of producing high-quality 1024px images in a few steps.
- vendor
- ByteDance · Stable Diffusion XL Lightning
ailicense unknown
model/stable-diffusion-xl-lightningv1.0.0model-atoms.com
text-generationstable
stable-beluga
Llama 2 based model fine tuned on an Orca-style dataset. Originally called Free Willy.
- vendor
- Stability AI · Stable Beluga
- sizes
- 7b 13b 70b
- ollama
ollama pull stable-beluga
ailicense unknown
model/stable-belugav1.0.0ollama.com/library
code-generationstable
stable-code
Stable Code 3B is a coding model with instruct and code completion variants on par with models such as Code Llama 7B that are 2.5x larger.
- vendor
- Stability AI · Stable Code
- sizes
- 3b
- ollama
ollama pull stable-code
ailicense unknown
model/stable-codev1.0.0ollama.com/library
text-generationstable
stablelm-zephyr
A lightweight chat model allowing accurate, and responsive output without requiring high-end hardware.
- vendor
- Stability AI · StableLM
- sizes
- 3b
- ollama
ollama pull stablelm-zephyr
ailicense unknown
model/stablelm-zephyrv1.0.0ollama.com/library
text-generationstable
stablelm2
Stable LM 2 is a state-of-the-art 1.6B and 12B parameter language model trained on multilingual data in English, Spanish, German, Italian, French, Portuguese, and Dutch.
- vendor
- Stability AI · StableLM
- sizes
- 1.6b 12b
- ollama
ollama pull stablelm2
ailicense unknown
model/stablelm2v1.0.0ollama.com/library
code-generationstable
starcoder
StarCoder is a code generation model trained on 80+ programming languages.
- vendor
- BigCode · StarCoder
- sizes
- 1b 3b 7b 15b
- ollama
ollama pull starcoder
ailicense unknown
model/starcoderv1.0.0ollama.com/library
code-generationstable
starcoder2
StarCoder2 is the next generation of transparently trained open code LLMs that comes in three sizes: 3B, 7B and 15B parameters.
- vendor
- BigCode · StarCoder
- sizes
- 3b 7b 15b
- ollama
ollama pull starcoder2
ailicense unknown
model/starcoder2v1.0.0ollama.com/library
text-generationstable
starling-lm
Starling is a large language model trained by reinforcement learning from AI feedback focused on improving chatbot helpfulness.
- vendor
- Berkeley · Starling
- sizes
- 7b
- ollama
ollama pull starling-lm
ailicense unknown
model/starling-lmv1.0.0ollama.com/library
text-generationstable
tinydolphin
An experimental 1.1B parameter model trained on the new Dolphin 2.8 dataset by Eric Hartford and based on TinyLlama.
- vendor
- Cognitive Computations · Dolphin
- sizes
- 1.1b
- ollama
ollama pull tinydolphin
ailicense unknown
model/tinydolphinv1.0.0ollama.com/library
text-generationstable
tinyllama
The TinyLlama project is an open endeavor to train a compact 1.1B Llama model on 3 trillion tokens.
- vendor
- TinyLlama · TinyLlama
- sizes
- 1.1b
- ollama
ollama pull tinyllama
ailicense unknown
model/tinyllamav1.0.0ollama.com/library
multimodalstable
translategemma
A new collection of open translation models built on Gemma 3, helping people communicate across 55 languages.
- vendor
- Google · TranslateGemma
- sizes
- 4b 12b 27b
- ollama
ollama pull translategemma
model/translategemmav1.0.1ollama.com/library
text-generationstable
tulu3
Tülu 3 is a leading instruction following model family, offering fully open-source data, code, and recipes by the The Allen Institute for AI.
- vendor
- AI2 · Tülu
- sizes
- 8b 70b
- ollama
ollama pull tulu3
ailicense unknown
model/tulu3v1.0.0ollama.com/library
multimodalstable
UForm Gen2 Qwen 500M
Small generative vision-language model primarily designed for image captioning and visual question answering.
- vendor
- Unum · UForm
model/uform-gen2-qwen-500mv1.0.0model-atoms.com
text-generationstable
vicuna
General use chat model based on Llama and Llama 2 with 2K to 16K context sizes.
- vendor
- LMSYS · Vicuna
- sizes
- 7b 13b 33b
- ollama
ollama pull vicuna
ailicense unknown
model/vicunav1.0.0ollama.com/library
otherstable
Whisper
General-purpose speech recognition model supporting multilingual recognition, speech translation, and language identification.
- vendor
- OpenAI · Whisper
ailicense unknown
model/whisperv1.0.0model-atoms.com
otherstable
Whisper Large v3 Turbo
Pre-trained model for automatic speech recognition (ASR) and speech translation.
- vendor
- OpenAI · Whisper
model/whisper-large-v3-turbov1.0.0model-atoms.com
otherstable
Whisper Tiny EN
English-only version of the Whisper Tiny model trained on speech recognition.
- vendor
- OpenAI · Whisper
ailicense unknown
model/whisper-tiny-env1.0.0model-atoms.com
text-generationstable
wizard-math
Model focused on math and logic problems
- vendor
- WizardLM · WizardMath
- sizes
- 7b 13b 70b
- ollama
ollama pull wizard-math
ailicense unknown
model/wizard-mathv1.0.0ollama.com/library
text-generationstable
wizard-vicuna
Wizard Vicuna is a 13B parameter model based on Llama 2 trained by MelodysDreamj.
- vendor
- WizardLM · Wizard Vicuna
- sizes
- 13b
- ollama
ollama pull wizard-vicuna
ailicense unknown
model/wizard-vicunav1.0.0ollama.com/library
text-generationstable
wizard-vicuna-uncensored
Wizard Vicuna Uncensored is a 7B, 13B, and 30B parameter model based on Llama 2 uncensored by Eric Hartford.
- vendor
- WizardLM · Wizard Vicuna
- sizes
- 7b 13b 30b
- ollama
ollama pull wizard-vicuna-uncensored
ailicense unknown
model/wizard-vicuna-uncensoredv1.0.0ollama.com/library
code-generationstable
wizardcoder
State-of-the-art code generation model
- vendor
- WizardLM · WizardCoder
- sizes
- 33b
- ollama
ollama pull wizardcoder
ailicense unknown
model/wizardcoderv1.0.0ollama.com/library
text-generationstable
wizardlm
General use model based on Llama 2.
- vendor
- WizardLM · WizardLM
- ollama
ollama pull wizardlm
ailicense unknown
model/wizardlmv1.0.0ollama.com/library
text-generationstable
wizardlm-uncensored
Uncensored version of Wizard LM model
- vendor
- WizardLM · WizardLM
- sizes
- 13b
- ollama
ollama pull wizardlm-uncensored
ailicense unknown
model/wizardlm-uncensoredv1.0.0ollama.com/library
text-generationstable
wizardlm2
State of the art large language model from Microsoft AI with improved performance on complex chat, multilingual, reasoning and agent use cases.
- vendor
- WizardLM · WizardLM
- sizes
- 7b 8x22b
- ollama
ollama pull wizardlm2
ailicense unknown
model/wizardlm2v1.0.0ollama.com/library
text-generationstable
xwinlm
Conversational model based on Llama 2 that performs competitively on various benchmarks.
- vendor
- Xwin-LM · Xwin-LM
- sizes
- 7b 13b
- ollama
ollama pull xwinlm
ailicense unknown
model/xwinlmv1.0.0ollama.com/library
text-generationstable
yarn-llama2
An extension of Llama 2 that supports a context of up to 128k tokens.
- vendor
- Nous Research · YaRN
- sizes
- 7b 13b
- ollama
ollama pull yarn-llama2
ailicense unknown
model/yarn-llama2v1.0.0ollama.com/library
text-generationstable
yarn-mistral
An extension of Mistral to support context windows of 64K or 128K.
- vendor
- Nous Research · YaRN
- sizes
- 7b
- ollama
ollama pull yarn-mistral
ailicense unknown
model/yarn-mistralv1.0.0ollama.com/library
text-generationstable
yi
Yi 1.5 is a high-performing, bilingual language model.
- vendor
- 01.AI · Yi
- sizes
- 6b 9b 34b
- ollama
ollama pull yi
ailicense unknown
model/yiv1.0.0ollama.com/library
code-generationstable
yi-coder
Yi-Coder is a series of open-source code language models that delivers state-of-the-art coding performance with fewer than 10 billion parameters.
- vendor
- 01.AI · Yi
- sizes
- 1.5b 9b
- ollama
ollama pull yi-coder
ailicense unknown
model/yi-coderv1.0.0ollama.com/library
text-generationstable
zephyr
Zephyr is a series of fine-tuned versions of the Mistral and Mixtral models that are trained to act as helpful assistants.
- vendor
- Hugging Face · Zephyr
- sizes
- 7b 141b
- ollama
ollama pull zephyr
ailicense unknown
model/zephyrv1.0.0ollama.com/library
Nothing matches. Clear a filter or try the global search (/).