Ollama
Models GitHub Discord Docs Cloud
Sign in Download
Models Download GitHub Discord Docs Cloud Sign in
⇅
deep · Ollama Search
Search for models on Ollama.
  • deepseek-r1

    DeepSeek-R1 is a family of open reasoning models with performance approaching that of leading models, such as O3 and Gemini 2.5 Pro.

    tools thinking 1.5b 7b 8b 14b 32b 70b 671b

    73.6M  Pulls 35  Tags Updated  5 months ago

  • deepseek-v3.1

    DeepSeek-V3.1-Terminus is a hybrid model that supports both thinking mode and non-thinking mode.

    tools thinking cloud 671b

    183.4K  Pulls 8  Tags Updated  2 months ago

  • deepseek-v3

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

    671b

    2.9M  Pulls 5  Tags Updated  10 months ago

  • deepseek-coder

    DeepSeek Coder is a capable coding model trained on two trillion code and natural language tokens.

    1.3b 6.7b 33b

    2.1M  Pulls 102  Tags Updated  1 year 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

    1.2M  Pulls 64  Tags Updated  1 year ago

  • deepscaler

    A fine-tuned version of Deepseek-R1-Distilled-Qwen-1.5B that surpasses the performance of OpenAI’s o1-preview with just 1.5B parameters on popular math evaluations.

    1.5b

    784.2K  Pulls 5  Tags Updated  9 months ago

  • deepcoder

    DeepCoder is a fully open-Source 14B coder model at O3-mini level, with a 1.5B version also available.

    1.5b 14b

    424.8K  Pulls 9  Tags Updated  8 months ago

  • deepseek-llm

    An advanced language model crafted with 2 trillion bilingual tokens.

    7b 67b

    228.6K  Pulls 64  Tags Updated  1 year ago

  • deepseek-v2

    A strong, economical, and efficient Mixture-of-Experts language model.

    16b 236b

    216.9K  Pulls 34  Tags Updated  1 year ago

  • deepseek-v2.5

    An upgraded version of DeekSeek-V2 that integrates the general and coding abilities of both DeepSeek-V2-Chat and DeepSeek-Coder-V2-Instruct.

    236b

    83.9K  Pulls 7  Tags Updated  1 year ago

  • deepseek-ocr

    DeepSeek-OCR is a vision-language model that can perform token-efficient OCR.

    vision 3b

    44.4K  Pulls 3  Tags Updated  2 weeks ago

  • gemma

    Gemma is a family of lightweight, state-of-the-art open models built by Google DeepMind. Updated to version 1.1

    2b 7b

    5.6M  Pulls 102  Tags Updated  1 year ago

  • cogito

    Cogito v1 Preview is a family of hybrid reasoning models by Deep Cogito that outperform the best available open models of the same size, including counterparts from LLaMA, DeepSeek, and Qwen across most standard benchmarks.

    tools 3b 8b 14b 32b 70b

    845.7K  Pulls 20  Tags Updated  8 months ago

  • openthinker

    A fully open-source family of reasoning models built using a dataset derived by distilling DeepSeek-R1.

    7b 32b

    619.7K  Pulls 15  Tags Updated  8 months ago

  • exaone-deep

    EXAONE Deep exhibits superior capabilities in various reasoning tasks including math and coding benchmarks, ranging from 2.4B to 32B parameters developed and released by LG AI Research.

    2.4b 7.8b 32b

    289.3K  Pulls 13  Tags Updated  8 months ago

  • r1-1776

    A version of the DeepSeek-R1 model that has been post trained to provide unbiased, accurate, and factual information by Perplexity.

    70b 671b

    145.1K  Pulls 9  Tags Updated  9 months ago

  • gemma3n

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

    e2b e4b

    857K  Pulls 9  Tags Updated  5 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

    94.7K  Pulls 33  Tags Updated  2 years ago

  • command-r7b

    The smallest model in Cohere's R series delivers top-tier speed, efficiency, and quality to build powerful AI applications on commodity GPUs and edge devices.

    tools 7b

    91K  Pulls 5  Tags Updated  10 months ago

  • ministral-3

    The Ministral 3 family is designed for edge deployment, capable of running on a wide range of hardware.

    vision tools cloud 3b 8b 14b

    32.6K  Pulls 16  Tags Updated  2 days ago

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