Ollama
Models Docs Pricing
Sign in Download
Models Download Docs Pricing Sign in
⇅
gemma3 · Ollama
Search for models on Ollama.
  • gemma3

    The current, most capable model that runs on a single GPU.

    vision 270m 1b 4b 12b 27b

    39M  Pulls 26  Tags Updated  11 months ago

  • gemma3n

    Gemma 3n models are designed for efficient execution on everyday devices such as laptops, tablets or phones.

    e2b e4b

    1.9M  Pulls 9  Tags Updated  1 year ago

  • medgemma

    MedGemma is a collection of Gemma 3 variants that are trained for performance on medical text and image comprehension.

    vision 4b 27b

    212.8K  Pulls 9  Tags Updated  3 months ago

  • translategemma

    A new collection of open translation models built on Gemma 3, helping people communicate across 55 languages.

    vision 4b 12b 27b

    1.9M  Pulls 13  Tags Updated  6 months ago

  • embeddinggemma

    EmbeddingGemma is a 300M parameter embedding model from Google.

    embedding 300m

    1.5M  Pulls 5  Tags Updated  10 months ago

  • functiongemma

    FunctionGemma is a specialized version of Google's Gemma 3 270M model fine-tuned explicitly for function calling.

    tools 270m

    175.3K  Pulls 4  Tags Updated  7 months ago

  • glm4

    A strong multi-lingual general language model with competitive performance to Llama 3.

    9b

    1.2M  Pulls 32  Tags Updated  2 years ago

  • HammerAI/mars-gemma3

    OddTheGreat/Mars_27B_V.1

    tools

    280  Pulls 9  Tags Updated  4 weeks ago

  • imranzunzani/gemma3-1b-owui-fix

    Fixes the issue with Open WebUI not passing tools (native) and system prompt information properly. num_ctx default: 32768. Tested with Open WebUI v0.9.6 and v0.10.2. Just built on top of https://ollama.com/library/gemma3:1b.

    tools

    23  Pulls 1  Tag Updated  1 week ago

  • os-w/open-assistans-v3

    This is an AI model based on the Gemma3 Model Family, but designed to address issues such as sycophancy or unnecessary praise that may arise in AI models. This has no connection to the OpenAssistans project; this AI model was created by OpenSoftware-World

    vision 270m 1b 4b 12b 27b

    17  Pulls 6  Tags Updated  2 weeks ago

  • coney_/gemma3_claude-sonnet4.6

    gemma3_claude-sonnet4.6 is the Gemma 3 model running on the Claude Sonnet 4.6 system prompt, combining Gemma 3's open-source foundation with Claude Sonnet 4.6's instructions and behavior.

    vision

    976  Pulls 1  Tag Updated  4 months ago

  • samuser3/granite3.2-gemma3

    Granite3.2-Gemma3 is a lightweight, efficient AI model designed for daily conversation, code generation, text analysis and multimodal understanding, delivering stable and responsive performance for various daily tasks.

    vision tools thinking 1b 4b

    833  Pulls 4  Tags Updated  4 months ago

  • os-w/open-health-assistans-v1

    This is an AI model based on the Gemma3 Model Family and designed to help people with health issues. This model has no connection to the OpenAssistans project; it was created by OpenSoftware-World. (You are responsible for this. Please use it carefully.)

    vision 270m 1b 4b 12b 27b

    13  Pulls 6  Tags Updated  2 weeks ago

  • dhiltgen/gemma3

    Testing new conversion patterns...

    vision 270m 1b 4b 12b 27b

    479  Pulls 81  Tags Updated  3 days ago

  • vishalraj/gemma3-27b-abliterated

    vision

    484  Pulls 1  Tag Updated  5 months ago

  • nexusriot/gemma3-abliterated

    vision 4b 12b

    311  Pulls 2  Tags Updated  3 months ago

  • dhiltgen/gemma3n

    vision e2b e4b

    266  Pulls 21  Tags Updated  1 week ago

  • edyrkaj/gemma3-1b-translator

    Isolate the response only for translation purposes

    141  Pulls 1  Tag Updated  5 months ago

  • mdq100/Gemma3-Instruct-Abliterated

    Gemma3-Instruct-Abliterated model is an instruction-tuned, abliterated, and uncensored AI model built on the Gemma-3 instruction-tuned model from Hugging Face. This Ollama model provides free, honest, and uncensored responses while remaining coherent

    vision 12b 27b

    23.1K  Pulls 2  Tags Updated  10 months ago

  • VladimirGav/gemma3-27b-16GB-VRAM

    87  Pulls 1  Tag Updated  3 months ago

© 2026 Ollama
Blog Contact