Ollama
Models GitHub Discord Docs Cloud
Sign in Download
Models Download GitHub Discord Docs Cloud Sign in
⇅
mmamama · Ollama Search
Search for models on Ollama.
  • mathstral

    MathΣtral: a 7B model designed for math reasoning and scientific discovery by Mistral AI.

    7b

    56.1K  Pulls 17  Tags Updated  1 year ago

  • qwen2-math

    Qwen2 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).

    1.5b 7b 72b

    172.5K  Pulls 52  Tags Updated  1 year ago

  • meditron

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

    7b 70b

    91.3K  Pulls 22  Tags Updated  1 year ago

  • wizardlm2

    State of the art large language model from Microsoft AI with improved performance on complex chat, multilingual, reasoning and agent use cases.

    7b 8x22b

    454K  Pulls 22  Tags Updated  1 year 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

    79.7K  Pulls 33  Tags Updated  1 year ago

  • mannix/qwen2-math-7b

    Qwen2-Math is a series of specialized math language models built upon the Qwen2 LLMs

    629  Pulls 21  Tags Updated  1 year ago

  • mannix/qwen2-math-1.5b

    Qwen2-Math is a series of specialized math language models built upon the Qwen2 LLMs

    112  Pulls 7  Tags Updated  1 year ago

  • MeaTLoTioN/Marge_Simpson

    Marge Simpson is the loving, patient, and often-overlooked matriarch of the Simpson family. With her iconic blue beehive, she balances chaos with wisdom, keeping Homer and their kids in line.

    tools

    27  Pulls 1  Tag Updated  6 months ago

  • milkey/Qihoo360-Light-R1-14B-DS

    Light-R1-14B-DS is the State-Of-The-Art 14B math model with AIME24 & 25 scores 74.0 & 60.2, outperforming many 32B models.

    297  Pulls 1  Tag Updated  6 months ago

  • mithun/magicoder

    🎩Magicoder is a model family empowered by 🪄OSS-Instruct, a novel approach to enlightening LLMs with open-source code snippets for generating low-bias and high-quality instruction data for code.

    262  Pulls 6  Tags Updated  1 year ago

  • Mohamed_Omar/marketer

    You are a seasoned AI and marketing expert with deep expertise in developing specialized AI models for business applications. I would like to leverage your knowledge to design a highly functional Ollama model tailored specifically for marketing profession

    tools

    2  Pulls 1  Tag Updated  1 month ago

  • monotykamary/medichat-llama3

    Built upon the powerful LLaMa-3 architecture and fine-tuned on an extensive dataset of health information, this model leverages its vast medical knowledge to offer clear, comprehensive answers.

    8b

    2,699  Pulls 6  Tags Updated  1 year ago

  • mightykatun/qwen2.5-math

    An enhanced mathematical reasoning model that combines Chain-of-Thought (CoT) and Tool-integrated Reasoning (TIR).

    1.5b 7b 72b

    1,011  Pulls 3  Tags Updated  10 months ago

  • impactframes/stable_diffusion_prompt_maker

    Use w/ IF prompt maker extension forge, Next & A1111. This is a LLaMa2 7b base model, that I made when llama2 came out, to make SD format prompts. The GPTQ version works better than this but I lost the metadata and can't make it into GGUF.

    843  Pulls 1  Tag Updated  1 year ago

  • mcgdj/gpt-oss-6.0b

    A smaller, experimental model of gpt-oss:20b. From https://huggingface.co/AmanPriyanshu/gpt-oss-6.0b-specialized-all-pruned-moe-only-7-experts

    255  Pulls 1  Tag Updated  1 month ago

  • mertbozkir/metamath-mistral-7b

    TheBloke/MetaMath-Mistral-7B-GGUF

    108  Pulls 3  Tags Updated  1 year ago

  • smartkit/manuscriptmaster

    mastering your manuscript, GPTS:https://chat.openai.com/g/g-qweCAttn4-manuscript-master

    52  Pulls 1  Tag Updated  1 year ago

  • MHKetbi/AceMath-72B-Instruct

    model excel at solving English mathematical problems using Chain-of-Thought (CoT) reasoning available in [F16, q8_0, q6_K, q4_K_S]

    33  Pulls 4  Tags Updated  7 months ago

  • martindisley/unlearning-to-rest

    Unlearning to Rest is an ablated and repaired version of Meta's Llama 3.2:3B. Modifications have been made to the original's parameters to suppress its knowledge of the concept of the 'chair'.

    22  Pulls 1  Tag Updated  5 months ago

  • etangaming123/mai

    gemma3:4b but mai from bunny girl senpai [made for a schoolfriend] (info taken from https://aobuta.fandom.com/wiki/Mai_Sakurajima)

    vision

    13  Pulls 1  Tag Updated  1 month ago

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