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

    40.3M  Pulls 26  Tags Updated  1 year ago

  • gemma3n

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

    e2b e4b

    2.2M  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

    372K  Pulls 9  Tags Updated  4 months ago

  • translategemma

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

    vision 4b 12b 27b

    2.3M  Pulls 13  Tags Updated  7 months ago

  • functiongemma

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

    tools 270m

    188.5K  Pulls 4  Tags Updated  8 months ago

  • embeddinggemma

    EmbeddingGemma is a 300M parameter embedding model from Google.

    embedding 300m

    2.1M  Pulls 5  Tags Updated  1 year 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

  • babar_jamali/gemma3-abliterated-1b

    Gemma 3-270M abliterated small size and redefined AI Model for faster tasks related to general purpose, cybersecurity, coding and research.

    220  Pulls 2  Tags Updated  3 weeks ago

  • babar_jamali/gemma3-abliterated-270m

    Gemma 3-270M abliterated small size and redefined AI Model for faster tasks related to general purpose, cybersecurity, coding and research.

    49  Pulls 2  Tags Updated  3 weeks 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

    1,107  Pulls 4  Tags Updated  5 months ago

  • HammerAI/mars-gemma3

    OddTheGreat/Mars_27B_V.1

    tools

    583  Pulls 9  Tags Updated  2 months ago

  • dhiltgen/gemma3

    Testing new conversion patterns...

    vision 270m 1b 4b 12b 27b

    543  Pulls 81  Tags Updated  1 month ago

  • nexusriot/gemma3-abliterated

    vision 4b 12b

    363  Pulls 2  Tags Updated  5 months ago

  • dhiltgen/gemma3n

    vision e2b e4b

    293  Pulls 21  Tags Updated  1 month ago

  • richards_michael/gemma3

    vision 4b

    9  Pulls 1  Tag Updated  2 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

    116  Pulls 1  Tag Updated  1 month 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

    23.8K  Pulls 2  Tags Updated  11 months ago

  • VladimirGav/gemma3-27b-16GB-VRAM

    96  Pulls 1  Tag Updated  5 months ago

  • jayeshpandit2480/gemma3-UNCENSORED

    These are essentially Completely UNCENSORED versions of GEMMA3 1B and 4B. Just NJOY!!!

    vision 1b 4b

    7,841  Pulls 2  Tags Updated  8 months ago

  • moophlo/soob3123_amoral-gemma3-12B-v2-GGUF

    55  Pulls 2  Tags Updated  5 months ago

© 2026 Ollama
Blog Support