{
  "schema": "https://ai-atoms.com/schemas/model-v1.json",
  "type": "model",
  "id": "model/llava",
  "version": "1.0.0",
  "name": "llava",
  "description": "🌋 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",
  "family": "LLaVA",
  "task": "multimodal",
  "capabilities": [
    "vision"
  ],
  "parameter_sizes": [
    "7b",
    "13b",
    "34b"
  ],
  "providers": [
    {
      "name": "Ollama",
      "model_id": "llava",
      "url": "https://ollama.com/library/llava",
      "pull_command": "ollama pull llava",
      "run_command": "ollama run llava",
      "tag_count": 98,
      "pulls": "14.8M",
      "updated_at": "2024-02-01"
    }
  ],
  "links": {
    "model_card": "https://ollama.com/library/llava"
  },
  "authored_by": "LLaVA",
  "source_url": "https://ollama.com/library/llava",
  "category": "ai",
  "provenance": {
    "source": "ollama.com/library",
    "source_url": "https://ollama.com/library/llava",
    "license": "unknown",
    "imported_at": "2026-09-03",
    "notes": "Description, capabilities, sizes, pulls, tag count and updated date as shown on the Ollama library page. Vendor, family and task are inferred from the model name; weights license is not published on the listing."
  },
  "tags": [
    "ollama",
    "local",
    "vision"
  ],
  "lifecycle": "stable"
}