category · ai
Automate ActiveCampaign tasks via Rube MCP (Composio): manage contacts, tags, list subscriptions, automation enrollment, and tasks. Always search tools first for current schemas.
/activecampaign-automationTesting and benchmarking LLM agents including behavioral testing, capability assessment, reliability metrics, and production monitoring—where even top agents achieve less than 50% on re...
/agent-evaluationManage multiple local CLI agents via tmux sessions (start/stop/monitor/assign) with cron-friendly scheduling.
/agent-manager-skillA hybrid memory system that provides persistent, searchable knowledge management for AI agents (Architecture, Patterns, Decisions).
/agent-memory-mcpMemory is the cornerstone of intelligent agents. Without it, every interaction starts from zero. This skill covers the architecture of agent memory: short-term (context window), long-term (vector s...
/agent-memory-systemsSystematic improvement of existing agents through performance analysis, prompt engineering, and continuous iteration.
/agent-orchestration-improve-agentBreak down complex user requests into smaller, manageable sub-tasks for multi-agent systems and individual agent workflows.
/agent-task-decompositionA seasoned AI engineer specializing in building, deploying, and optimizing large language model (LLM) applications and agentic systems.
/ai-engineerThey don't just follow instructions; they figure out what needs to be done. This skill covers agent architectures from simple loops to complex planning systems.
/autonomous-agentsExpert blockchain development including smart contract architecture, protocol design, security auditing, and decentralized application (dApp) implementation across multiple networks.
/blockchain-developerDeep semantic analysis of codebases, architectures, and patterns to provide accurate explanations and insights.
/code-understandingBridging the gap between messy user requirements and clean technical architecture through deep conceptual mapping and semantic modeling.
/conceptual-analystA robust conversational model designed to be used for both chat and instruct use cases.
ollama pull alfredEmbedding models on very large sentence level datasets.
ollama pull all-minilmAthene-V2 is a 72B parameter model which excels at code completion, mathematics, and log extraction tasks.
ollama pull athene-v2Context-aware text-to-speech model applying natural pacing and expressiveness.
Context-aware English text-to-speech model that applies natural pacing, expressiveness, and fillers based on context.
Context-aware Spanish text-to-speech model that applies natural pacing, expressiveness, and fillers based on context.
Aya 23, released by Cohere, is a new family of state-of-the-art, multilingual models that support 23 languages.
ollama pull ayaCohere For AI's language models trained to perform well across 23 different languages.
ollama pull aya-expanseBakLLaVA is a multimodal model consisting of the Mistral 7B base model augmented with the LLaVA architecture.
ollama pull bakllavaA state-of-the-art fact-checking model developed by Bespoke Labs.
ollama pull bespoke-minicheckGeneral embedding base model transforming text into 768-dimensional vectors.
General embedding large model transforming text into 1024-dimensional vectors.
Reranker model that takes question and document as input and outputs a relevance similarity score.
General embedding small model transforming text into 384-dimensional vectors.
Embedding model from BAAI mapping texts to vectors.
ollama pull bge-largeBGE-M3 is a new model from BAAI distinguished for its versatility in Multi-Functionality, Multi-Linguality, and Multi-Granularity.
ollama pull bge-m3A high-performing code instruct model created by merging two existing code models.
ollama pull codeboogaA versatile model for AI software development scenarios, including code completion.
ollama pull codegeex4CodeGemma 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.
ollama pull codegemmaA large language model that can use text prompts to generate and discuss code.
ollama pull codellamaCodeQwen1.5 is a large language model pretrained on a large amount of code data.
ollama pull codeqwenCodestral is Mistral AI’s first-ever code model designed for code generation tasks.
ollama pull codestralGreat code generation model based on Llama2.
ollama pull codeupCogito 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.
ollama pull cogitoThe Cogito v2.1 LLMs are instruction tuned generative models. All models are released under MIT license for commercial use.
ollama pull cogito-2.1111 billion parameter model optimized for demanding enterprises that require fast, secure, and high-quality AI
ollama pull command-aCommand R is a Large Language Model optimized for conversational interaction and long context tasks.
ollama pull command-rCommand R+ is a powerful, scalable large language model purpose-built to excel at real-world enterprise use cases.
ollama pull command-r-plusThe 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.
ollama pull command-r7bA 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.
ollama pull command-r7b-arabicDBRX is an open, general-purpose LLM created by Databricks.
ollama pull dbrxDeepCoder is a fully open-Source 14B coder model at O3-mini level, with a 1.5B version also available.
ollama pull deepcoderA 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.
ollama pull deepscalerDistilled from DeepSeek-R1 based on Qwen2.5; outperforms OpenAI o1-mini on several benchmarks.
DeepSeek Coder is a capable coding model trained on two trillion code and natural language tokens.
ollama pull deepseek-coderAn open-source Mixture-of-Experts code language model that achieves performance comparable to GPT4-Turbo in code-specific tasks.
ollama pull deepseek-coder-v2An advanced language model crafted with 2 trillion bilingual tokens.
ollama pull deepseek-llmDeepSeek-OCR is a vision-language model that can perform token-efficient OCR.
ollama pull deepseek-ocrDeepSeek-R1 is a family of open reasoning models with performance approaching that of leading models, such as O3 and Gemini 2.5 Pro.
ollama pull deepseek-r1A strong, economical, and efficient Mixture-of-Experts language model.
ollama pull deepseek-v2An upgraded version of DeekSeek-V2 that integrates the general and coding abilities of both DeepSeek-V2-Chat and DeepSeek-Coder-V2-Instruct.
ollama pull deepseek-v2.5A strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token.
ollama pull deepseek-v3DeepSeek-V3.1-Terminus is a hybrid model that supports both thinking mode and non-thinking mode.
ollama pull deepseek-v3.1DeepSeek-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.
ollama pull deepseek-v4-flashDeepSeek-V4-Pro is a frontier Mixture-of-Experts model with a large context window and three reasoning modes.
ollama pull deepseek-v4-proDETection TRansformer model trained end-to-end on COCO 2017 object detection dataset (118k annotated images).
Devstral: the best open source model for coding agents
ollama pull devstral123B model that excels at using tools to explore codebases, editing multiple files and power software engineering agents.
ollama pull devstral-224B model that excels at using tools to explore codebases, editing multiple files and power software engineering agents.
ollama pull devstral-small-2Distilled BERT model fine-tuned on SST-2 for sentiment classification.
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.
ollama pull dolphin-llama3The uncensored Dolphin model based on Mistral that excels at coding tasks. Updated to version 2.8.
ollama pull dolphin-mistralUncensored, 8x7b and 8x22b fine-tuned models based on the Mixtral mixture of experts models that excels at coding tasks. Created by Eric Hartford.
ollama pull dolphin-mixtral2.7B uncensored Dolphin model by Eric Hartford, based on the Phi language model by Microsoft Research.
ollama pull dolphin-phiDolphin 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.
ollama pull dolphin3A 7B and 15B uncensored variant of the Dolphin model family that excels at coding, based on StarCoder2.
ollama pull dolphincoderStable Diffusion model fine-tuned to be better at photorealism.
7B parameter text-to-SQL model made by MotherDuck and Numbers Station.
ollama pull duckdb-nsqlEmbeddingGemma is a 300M parameter embedding model from Google.
ollama pull embeddinggemmaUncensored Llama2 based model with support for a 16K context window.
ollama pull everythinglmEXAONE 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.
ollama pull exaone-deepEXAONE 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.
ollama pull exaone3.5A large language model built by the Technology Innovation Institute (TII) for use in summarization, text generation, and chat bots.
ollama pull falconFalcon2 is an 11B parameters causal decoder-only model built by TII and trained over 5T tokens.
ollama pull falcon2A family of efficient AI models under 10B parameters performant in science, math, and coding through innovative training techniques.
ollama pull falcon3An open weights function calling model based on Llama 3, competitive with GPT-4o function calling capabilities.
ollama pull firefunction-v212 billion parameter rectified flow transformer capable of generating images from text descriptions.
Image model capable of generating highly realistic and detailed images with multi-reference support.
Ultra-fast distilled image model delivering state-of-the-art quality for interactive workflows and real-time previews.
Ultra-fast distilled image model with enhanced quality; unifies image generation and editing in a single model.
First conversational speech recognition model built specifically for voice agents.
FunctionGemma is a specialized version of Google's Gemma 3 270M model fine-tuned explicitly for function calling.
ollama pull functiongemmaGemma is a family of lightweight, state-of-the-art open models built by Google DeepMind. Updated to version 1.1
ollama pull gemmaSoutheast Asian Languages In One Network — LLMs pretrained and instruct-tuned for the Southeast Asia region.
Google Gemma 2 is a high-performing and efficient model available in three sizes: 2B, 9B, and 27B.
ollama pull gemma2The current, most capable model that runs on a single GPU.
ollama pull gemma3Gemma 3n models are designed for efficient execution on everyday devices such as laptops, tablets or phones.
ollama pull gemma3nGemma 4 models are designed to deliver frontier-level performance at each size. They are well-suited for reasoning, agentic workflows, coding, and multimodal understanding.
ollama pull gemma4As the strongest model in the 30B class, GLM-4.7-Flash offers a new option for lightweight deployment that balances performance and efficiency.
ollama pull glm-4.7-flashGLM-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.
ollama pull glm-5.1GLM-5.2 is Z.ai’s flagship model for the era of long-horizon tasks.
ollama pull glm-5.2Z.ai's flagship model and the most capable open-weights model for coding, with major gains on long-horizon agentic tasks.
ollama pull glm-5.3Z.ai's first natively multimodal model, approaching Claude Opus 4.8 on coding and agentic benchmarks with just 18B active parameters.
ollama pull glm-5.3-flashGLM-OCR is a multimodal OCR model for complex document understanding, built on the GLM-V encoder–decoder architecture.
ollama pull glm-ocrA strong multi-lingual general language model with competitive performance to Llama 3.
ollama pull glm4A language model created by combining two fine-tuned Llama 2 70B models into one.
ollama pull goliathOpenAI’s open-weight models designed for powerful reasoning, agentic tasks, and versatile developer use cases.
ollama pull gpt-ossgpt-oss-safeguard-20b and gpt-oss-safeguard-120b are safety reasoning models built-upon gpt-oss
ollama pull gpt-oss-safeguardIndustry-leading results in agentic tasks including instruction following and function calling; suited for RAG, multi-agent workflows, and edge deployments.
A family of open foundation models by IBM for Code Intelligence
ollama pull granite-codeThe 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.
ollama pull granite-embeddingThe 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.
ollama pull granite3-denseThe IBM Granite Guardian 3.0 2B and 8B models are designed to detect risks in prompts and/or responses.
ollama pull granite3-guardianThe IBM Granite 1B and 3B models are the first mixture of experts (MoE) Granite models from IBM designed for low latency usage.
ollama pull granite3-moeThe 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.
ollama pull granite3.1-denseThe IBM Granite 1B and 3B models are long-context mixture of experts (MoE) Granite models from IBM designed for low latency usage.
ollama pull granite3.1-moeGranite-3.2 is a family of long-context AI models from IBM Granite fine-tuned for thinking capabilities.
ollama pull granite3.2A compact and efficient vision-language model, specifically designed for visual document understanding, enabling automated content extraction from tables, charts, infographics, plots, diagrams, and more.
ollama pull granite3.2-visionIBM Granite 2B and 8B models are 128K context length language models that have been fine-tuned for improved reasoning and instruction-following capabilities.
ollama pull granite3.3Granite 4 features improved instruction following (IF) and tool-calling capabilities, making them more effective in enterprise applications.
ollama pull granite4IBM 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.
ollama pull granite4.1Granite Guardian 4.1 is a specialized safety and judging model from IBM Research that evaluates whether LLM prompts and responses meet specified harm criteria.
ollama pull granite4.1-guardianIBM 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.
ollama pull granite4.2Upgraded, retrained version of Nous Hermes 2 with function calling and JSON mode capabilities.
Hermes 3 is the latest version of the flagship Hermes series of LLMs by Nous Research
ollama pull hermes3First open-source transformer-based multilingual NMT model supporting high-quality translation across all 22 scheduled Indic languages.
InternLM2.5 is a 7B parameter model tailored for practical scenarios with outstanding reasoning capability.
ollama pull internlm2Frontier-scale open-source model with a 256k context window.
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.
ollama pull kimi-k2.6Kimi 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.
ollama pull kimi-k2.7-codeKimi K3 is an open-weight, native multimodal agentic model and our most capable model to date.
ollama pull kimi-k3Our most capable model to date, designed for long-horizon work. 70.2% on Terminal-Bench 2.1 at 118B-A8B.
ollama pull laguna-s-2.1Laguna 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.
ollama pull laguna-xs-2.1Laguna 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.
ollama pull laguna-xs.2LFM2 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.
ollama pull lfm2LFM2.5-8B-A1B, an edge model built for fast, reliable tool calling on consumer hardware.
ollama pull lfm2.5LFM2.5 is a new family of hybrid models designed for on-device deployment.
ollama pull lfm2.5-thinking17 billion parameter natively multimodal model with 16 experts (mixture-of-experts architecture).
Llama Guard 3 is a series of models fine-tuned for content safety classification of LLM inputs and responses.
ollama pull llama-guard3An expansion of Llama 2 that specializes in integrating both general language understanding and domain-specific knowledge, particularly in programming and mathematics.
ollama pull llama-proLlama 2 is a collection of foundation language models ranging from 7B to 70B parameters.
ollama pull llama2Llama 2 based model fine tuned to improve Chinese dialogue ability.
ollama pull llama2-chineseUncensored Llama 2 model by George Sung and Jarrad Hope.
ollama pull llama2-uncensoredMeta Llama 3: The most capable openly available LLM to date
ollama pull llama3A model from NVIDIA based on Llama 3 that excels at conversational question answering (QA) and retrieval-augmented generation (RAG).
ollama pull llama3-chatqaThis model extends LLama-3 8B's context length from 8k to over 1m tokens.
ollama pull llama3-gradientA series of models from Groq that represent a significant advancement in open-source AI capabilities for tool use/function calling.
ollama pull llama3-groq-tool-useLlama 3.1 is a new state-of-the-art model from Meta available in 8B, 70B and 405B parameter sizes.
ollama pull llama3.1Meta's Llama 3.2 goes small with 1B and 3B models.
ollama pull llama3.2Llama 3.2 Vision is a collection of instruction-tuned image reasoning generative models in 11B and 90B sizes.
ollama pull llama3.2-visionNew state of the art 70B model. Llama 3.3 70B offers similar performance compared to the Llama 3.1 405B model.
ollama pull llama3.3Meta's latest collection of multimodal models.
ollama pull llama4🌋 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.
ollama pull llavaOpen-source multimodal chatbot trained by fine-tuning LLaMA/Vicuna on visual instruction data; supports image captioning and visual question answering.
A LLaVA model fine-tuned from Llama 3 Instruct with better scores in several benchmarks.
ollama pull llava-llama3A new small LLaVA model fine-tuned from Phi 3 Mini.
ollama pull llava-phi3Most adaptable and prompt-responsive model with strengths in sharp graphic design, full-HD renders, and accurate text rendering.
Multilingual encoder-decoder model trained for many-to-many multilingual translation.
🎩 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.
ollama pull magicoderMagistral is a small, efficient reasoning model with 24B parameters.
ollama pull magistralAn open large reasoning model for real-world solutions by the Alibaba International Digital Commerce Group (AIDC-AI).
ollama pull marco-o1MathΣtral: a 7B model designed for math reasoning and scientific discovery by Mistral AI.
ollama pull mathstralMedGemma is a collection of Gemma 3 variants that are trained for performance on medical text and image comprehension.
ollama pull medgemmaMedGemma 1.5 4B is an updated version of the MedGemma 4B model.
ollama pull medgemma1.5Open-source medical large language model adapted from Llama 2 to the medical domain.
ollama pull meditronFine-tuned Llama 2 model to answer medical questions based on an open source medical dataset.
ollama pull medllama2MegaDolphin-2.2-120b is a transformation of Dolphin-2.2-70b created by interleaving the model with itself.
ollama pull megadolphinHigh-quality multi-lingual text-to-speech library.
A series of multimodal LLMs (MLLMs) designed for vision-language understanding.
ollama pull minicpm-vA GPT-4o Level MLLM for Single Image, Multi Image and High-FPS Video Understanding on Your Phone
ollama pull minicpm-v4.5A Pocket-Sized MLLM for Ultra-Efficient Image and Video Understanding on Your Phone
ollama pull minicpm-v4.6MiniMax's M2-series model for coding, agentic workflows, and professional productivity.
ollama pull minimax-m2.7MiniMax M3: Coding & Agentic Frontier. 1M context window. Native Multimodality.
ollama pull minimax-m3The Ministral 3 family is designed for edge deployment, capable of running on a wide range of hardware.
ollama pull ministral-3The 7B model released by Mistral AI, updated to version 0.3.
ollama pull mistralInstruct fine-tuned version of the Mistral-7B model.
32k context window instruct model with updated rope-theta and no sliding-window attention.
Mistral 7B instruct v0.2 dedicated for inference with LoRA adapters.
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.
ollama pull mistral-largeA general-purpose multimodal mixture-of-experts model for production-grade tasks and enterprise workloads.
ollama pull mistral-large-3Mistral 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.
ollama pull mistral-medium-3.5A state-of-the-art 12B model with 128k context length, built by Mistral AI in collaboration with NVIDIA.
ollama pull mistral-nemoMistral OpenOrca is a 7 billion parameter model, fine-tuned on top of the Mistral 7B model using the OpenOrca dataset.
ollama pull mistral-openorcaMistral Small 3 sets a new benchmark in the “small” Large Language Models category below 70B.
ollama pull mistral-smallBuilding 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.
ollama pull mistral-small3.1An update to Mistral Small that improves on function calling, instruction following, and less repetition errors.
ollama pull mistral-small3.2MistralLite is a fine-tuned model based on Mistral with enhanced capabilities of processing long contexts.
ollama pull mistralliteA set of Mixture of Experts (MoE) model with open weights by Mistral AI in 8x7b and 8x22b parameter sizes.
ollama pull mixtralmoondream2 is a small vision language model designed to run efficiently on edge devices.
ollama pull moondreamMeta'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.
ollama pull muse-glimmerState-of-the-art large embedding model from mixedbread.ai
ollama pull mxbai-embed-largeLlama-3.1-Nemotron-70B-Instruct is a large language model customized by NVIDIA to improve the helpfulness of LLM generated responses to user queries.
ollama pull nemotronNemotron-3-Nano is a new Standard for Efficient, Open, and Intelligent Agentic Models, now updated with a 4B parameter count model.
ollama pull nemotron-3-nanoNVIDIA 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.
ollama pull nemotron-3-superNVIDIA Nemotron 3 Ultra is built for high-throughput reasoning and long-running agent workflows.
ollama pull nemotron-3-ultraNVIDIA Nemotron 3.5 Lightning is an open 30B mixture-of-experts (MoE) model with 3B active parameters built for always-on agents.
ollama pull nemotron-3.5-lightningAn open 30B MoE model from NVIDIA with 3B activated parameters that delivers strong reasoning and agentic capabilities.
ollama pull nemotron-cascade-2A commercial-friendly small language model by NVIDIA optimized for roleplay, RAG QA, and function calling.
ollama pull nemotron-miniNVIDIA 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.
ollama pull nemotron3A fine-tuned model based on Mistral with good coverage of domain and language.
ollama pull neural-chatNexus Raven is a 13B instruction tuned model for function calling tasks.
ollama pull nexusravenA high-performing open embedding model with a large token context window.
ollama pull nomic-embed-textnomic-embed-text-v2-moe is a multilingual MoE text embedding model that excels at multilingual retrieval.
ollama pull nomic-embed-text-v2-moeNorth Mini Code is Cohere's first model for developers — a 30B Mixture-of-Experts model with 3B active parameters, built for agentic software engineering.
ollama pull north-mini-code-1.0A 7B chat model fine-tuned with high-quality data and based on Zephyr.
ollama pull notusA top-performing mixture of experts model, fine-tuned with high-quality data.
ollama pull notuxGeneral use models based on Llama and Llama 2 from Nous Research.
ollama pull nous-hermesThe powerful family of models by Nous Research that excels at scientific discussion and coding tasks.
ollama pull nous-hermes2The Nous Hermes 2 model from Nous Research, now trained over Mixtral.
ollama pull nous-hermes2-mixtralDeepgram speech-to-text model for transcribing audio.
A 3.8B model fine-tuned on a private high-quality synthetic dataset for information extraction, based on Phi-3.
ollama pull nuextractOlmo 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.
ollama pull olmo-3Olmo 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.
ollama pull olmo-3.1OLMo 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.
ollama pull olmo2Merge of the Open Orca OpenChat model and the Garage-bAInd Platypus 2 model. Designed for chat and code generation.
ollama pull open-orca-platypus2A family of open-source models trained on a wide variety of data, surpassing ChatGPT on various benchmarks. Updated to version 3.5-0106.
ollama pull openchatOpenCoder is an open and reproducible code LLM family which includes 1.5B and 8B models, supporting chat in English and Chinese languages.
ollama pull opencoderOpenHermes 2.5 is a 7B model fine-tuned by Teknium on Mistral with fully open datasets.
ollama pull openhermesA fully open-source family of reasoning models built using a dataset derived by distilling DeepSeek-R1.
ollama pull openthinkerA general-purpose model ranging from 3 billion parameters to 70 billion, suitable for entry-level hardware.
ollama pull orca-miniOrca 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.
ollama pull orca2A self-improving family of open-source models for agentic coding
ollama pull ornithChirp Chirp! 🐦 We are introducing Ornith-1.5, a major step toward building foundation models through end-to-end self-improvement.
ollama pull ornith-1.5Sentence-transformers model that can be used for tasks like clustering or semantic search.
ollama pull paraphrase-multilingualPhi-2: a 2.7B language model by Microsoft Research that demonstrates outstanding reasoning and language understanding capabilities.
ollama pull phiTransformer-based model with next-word prediction objective, trained on 1.4T tokens from web and synthetic sources.
Phi-3 is a family of lightweight 3B (Mini) and 14B (Medium) state-of-the-art open models by Microsoft.
ollama pull phi3A lightweight AI model with 3.8 billion parameters with performance overtaking similarly and larger sized models.
ollama pull phi3.5Phi-4 is a 14B parameter, state-of-the-art open model from Microsoft.
ollama pull phi4Phi-4-mini brings significant enhancements in multilingual support, reasoning, and mathematics, and now, the long-awaited function calling feature is finally supported.
ollama pull phi4-miniPhi 4 mini reasoning is a lightweight open model that balances efficiency with advanced reasoning ability.
ollama pull phi4-mini-reasoningPhi 4 reasoning and reasoning plus are 14-billion parameter open-weight reasoning models that rival much larger models on complex reasoning tasks.
ollama pull phi4-reasoningCode generation model based on Code Llama.
ollama pull phind-codellamaGenerates images with exceptional prompt adherence and coherent text rendering.
Japanese text embedding model that converts Japanese text input into numerical vectors for information retrieval, text classification, and clustering.
Qwen 1.5 is a series of large language models by Alibaba Cloud spanning from 0.5B to 110B parameters
ollama pull qwenQwen2 is a new series of large language models from Alibaba group
ollama pull qwen2Qwen2 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).
ollama pull qwen2-mathQwen2.5 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.
ollama pull qwen2.5The latest series of Code-Specific Qwen models, with significant improvements in code generation, code reasoning, and code fixing.
ollama pull qwen2.5-coderFlagship vision-language model of Qwen and also a significant leap from the previous Qwen2-VL.
ollama pull qwen2.5vlQwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models.
ollama pull qwen3Alibaba's performant long context models for agentic and coding tasks.
ollama pull qwen3-coderQwen3-Coder-Next is a coding-focused language model from Alibaba's Qwen team, optimized for agentic coding workflows and local development.
ollama pull qwen3-coder-nextBuilding upon the foundational models of the Qwen3 series, Qwen3 Embedding provides a comprehensive range of text embeddings models in various sizes
ollama pull qwen3-embeddingThe first installment in the Qwen3-Next series with strong performance in terms of both parameter efficiency and inference speed.
ollama pull qwen3-nextThe most powerful vision-language model in the Qwen model family to date.
ollama pull qwen3-vlQwen 3.5 is a family of open-source multimodal models that delivers exceptional utility and performance.
ollama pull qwen3.5Qwen3.6 delivers substantial upgrades in agentic coding and thinking preservation than previous Qwen models.
ollama pull qwen3.6Qwen3.8 delivers substantial gains across coding, professional work, research, and long-horizon agentic tasks.
ollama pull qwen3.8This experimental preview of the architecture that will underpin Qwen4.
ollama pull qwen3.8-flash-nextQwQ is the reasoning model of the Qwen series.
ollama pull qwqA version of the DeepSeek-R1 model that has been post trained to provide unbiased, accurate, and factual information by Perplexity.
ollama pull r1-1776A series of models that convert HTML content to Markdown content, which is useful for content conversion tasks.
ollama pull reader-lmA high-performing model trained with a new technique called Reflection-tuning that teaches a LLM to detect mistakes in its reasoning and correct course.
ollama pull reflection50 layers deep image classification CNN trained on more than 1 million images from the ImageNet dataset.
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.
ollama pull rnj-1Sailor2 are multilingual language models made for South-East Asia. Available in 1B, 8B, and 20B parameter sizes.
ollama pull sailor2A companion assistant trained in philosophy, psychology, and personal relationships. Based on Mistral.
ollama pull samantha-mistralShieldGemma 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.
ollama pull shieldgemmaA new small reasoning model fine-tuned from the Qwen 2.5 3B Instruct model.
ollama pull smallthinkerOpen source community-driven native audio turn detection model in its second version.
🪐 A family of small models with 135M, 360M, and 1.7B parameters, trained on a new high-quality dataset.
ollama pull smollmSmolLM2 is a family of compact language models available in three size: 135M, 360M, and 1.7B parameters.
ollama pull smollm2A suite of text embedding models by Snowflake, optimized for performance.
ollama pull snowflake-arctic-embedSnowflake's frontier embedding model. Arctic Embed 2.0 adds multilingual support without sacrificing English performance or scalability.
ollama pull snowflake-arctic-embed2A compact, yet powerful 10.7B large language model designed for single-turn conversation.
ollama pull solarSolar Pro Preview: an advanced large language model (LLM) with 22 billion parameters designed to fit into a single GPU
ollama pull solar-proSQLCoder is a code completion model fined-tuned on StarCoder for SQL generation tasks
ollama pull sqlcoderSQL-specialized model designed to help non-technical users understand and query data in SQL databases.
Generate a new image from an input image using Stable Diffusion.
Stable Diffusion model with inpainting capability using a mask to selectively edit image regions.
Diffusion-based text-to-image model that generates and modifies images based on text prompts.
Lightning-fast text-to-image generation model capable of producing high-quality 1024px images in a few steps.
Llama 2 based model fine tuned on an Orca-style dataset. Originally called Free Willy.
ollama pull stable-belugaStable 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.
ollama pull stable-codeA lightweight chat model allowing accurate, and responsive output without requiring high-end hardware.
ollama pull stablelm-zephyrStable 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.
ollama pull stablelm2StarCoder is a code generation model trained on 80+ programming languages.
ollama pull starcoderStarCoder2 is the next generation of transparently trained open code LLMs that comes in three sizes: 3B, 7B and 15B parameters.
ollama pull starcoder2Starling is a large language model trained by reinforcement learning from AI feedback focused on improving chatbot helpfulness.
ollama pull starling-lmAn experimental 1.1B parameter model trained on the new Dolphin 2.8 dataset by Eric Hartford and based on TinyLlama.
ollama pull tinydolphinThe TinyLlama project is an open endeavor to train a compact 1.1B Llama model on 3 trillion tokens.
ollama pull tinyllamaA new collection of open translation models built on Gemma 3, helping people communicate across 55 languages.
ollama pull translategemmaTülu 3 is a leading instruction following model family, offering fully open-source data, code, and recipes by the The Allen Institute for AI.
ollama pull tulu3Small generative vision-language model primarily designed for image captioning and visual question answering.
General use chat model based on Llama and Llama 2 with 2K to 16K context sizes.
ollama pull vicunaGeneral-purpose speech recognition model supporting multilingual recognition, speech translation, and language identification.
Pre-trained model for automatic speech recognition (ASR) and speech translation.
English-only version of the Whisper Tiny model trained on speech recognition.
Model focused on math and logic problems
ollama pull wizard-mathWizard Vicuna is a 13B parameter model based on Llama 2 trained by MelodysDreamj.
ollama pull wizard-vicunaWizard Vicuna Uncensored is a 7B, 13B, and 30B parameter model based on Llama 2 uncensored by Eric Hartford.
ollama pull wizard-vicuna-uncensoredState-of-the-art code generation model
ollama pull wizardcoderGeneral use model based on Llama 2.
ollama pull wizardlmUncensored version of Wizard LM model
ollama pull wizardlm-uncensoredState of the art large language model from Microsoft AI with improved performance on complex chat, multilingual, reasoning and agent use cases.
ollama pull wizardlm2Conversational model based on Llama 2 that performs competitively on various benchmarks.
ollama pull xwinlmAn extension of Llama 2 that supports a context of up to 128k tokens.
ollama pull yarn-llama2An extension of Mistral to support context windows of 64K or 128K.
ollama pull yarn-mistralYi 1.5 is a high-performing, bilingual language model.
ollama pull yiYi-Coder is a series of open-source code language models that delivers state-of-the-art coding performance with fewer than 10 billion parameters.
ollama pull yi-coderZephyr is a series of fine-tuned versions of the Mistral and Mixtral models that are trained to act as helpful assistants.
ollama pull zephyrNothing matches.