Ollama
Models GitHub Discord Turbo
Sign in Download
Models Download GitHub Discord Sign in
⇅
olma · Ollama Search
Search for models on Ollama.
  • 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.

    7b 13b

    2.6M  Pulls 9  Tags Updated  8 months ago

  • 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.

    7b 13b

    77.3K  Pulls 33  Tags Updated  1 year ago

  • mistral-nemo

    A state-of-the-art 12B model with 128k context length, built by Mistral AI in collaboration with NVIDIA.

    tools 12b

    2.5M  Pulls 17  Tags Updated  1 month ago

  • deepseek-v3

    A strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token.

    671b

    2.2M  Pulls 5  Tags Updated  8 months ago

  • deepseek-coder-v2

    An open-source Mixture-of-Experts code language model that achieves performance comparable to GPT4-Turbo in code-specific tasks.

    16b 236b

    1.1M  Pulls 64  Tags Updated  1 year ago

  • opencoder

    OpenCoder is an open and reproducible code LLM family which includes 1.5B and 8B models, supporting chat in English and Chinese languages.

    1.5b 8b

    135.2K  Pulls 9  Tags Updated  9 months ago

  • 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.

    1.5b 9b

    119.4K  Pulls 67  Tags Updated  12 months ago

  • meditron

    Open-source medical large language model adapted from Llama 2 to the medical domain.

    7b 70b

    88.6K  Pulls 22  Tags Updated  1 year ago

  • marco-o1

    An open large reasoning model for real-world solutions by the Alibaba International Digital Commerce Group (AIDC-AI).

    7b

    50.2K  Pulls 5  Tags Updated  9 months ago

  • open-orca-platypus2

    Merge of the Open Orca OpenChat model and the Garage-bAInd Platypus 2 model. Designed for chat and code generation.

    13b

    34.1K  Pulls 17  Tags Updated  1 year ago

  • 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.

    tools 7b

    17.5K  Pulls 5  Tags Updated  6 months ago

  • tinyllama

    The TinyLlama project is an open endeavor to train a compact 1.1B Llama model on 3 trillion tokens.

    1.1b

    2.8M  Pulls 36  Tags Updated  1 year ago

  • llama3.3

    New state of the art 70B model. Llama 3.3 70B offers similar performance compared to the Llama 3.1 405B model.

    tools 70b

    2.4M  Pulls 14  Tags Updated  9 months ago

  • 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.

    1.6b 12b

    128K  Pulls 84  Tags Updated  1 year ago

  • firefunction-v2

    An open weights function calling model based on Llama 3, competitive with GPT-4o function calling capabilities.

    tools 70b

    32.4K  Pulls 17  Tags Updated  1 year ago

  • ollamaced/gemma3_27b_pml_multiPDF_q4k_m

    This is a 8 bit quantized version of a gemma3:27b fine tuned with YagCed/Aveva_PML_test on HF. If you're from Aveva and want this model to be removed from public view, please let me know.

    55  Pulls 1  Tag Updated  3 months ago

  • ollamaced/gemma3_1b_spiders

    A very small test: gemma3:1b fine tuned with a dataset obsessed with spiders. As a result, this model puts spiders in all its answers. This is useless: just a pet project to learn to generate a dataset and fine tune a small model.

    35  Pulls 1  Tag Updated  4 months ago

  • omaciel/ticketeer-llama3.1

    Ticketeer is an experienced Agile Practitioner and Scrum Master.

    tools

    9  Pulls 1  Tag Updated  4 months ago

  • orbious/jin-developed-by-xiamen-labs

    Jin3.5-base based on Jin 3.5 max

    tools thinking

    4  Pulls 1  Tag Updated  4 days ago

  • adi0adi/ollama_stheno-8b_v3.1_q6k

    Model made ideally for 1-on-1 roleplay, but one that is able to handle scenarios, RPGs and storywriting fine. One of more capable among 8b, uses reliable L3.

    13.7K  Pulls 1  Tag Updated  1 year ago

© 2025 Ollama
Download Blog Docs GitHub Discord X (Twitter) Contact Us
  • Blog
  • Download
  • Docs
  • GitHub
  • Discord
  • X (Twitter)
  • Meetups
© 2025 Ollama Inc.