Ollama
Models Docs Pricing
Sign in Download
Models Download Docs Pricing Sign in
⇅
deepseek · Ollama
Search for models on Ollama.
  • deepseek-ocr

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

    vision 3b

    349.5K  Pulls 3  Tags Updated  4 months ago

  • deepseek-v3.2

    DeepSeek-V3.2, a model that harmonizes high computational efficiency with superior reasoning and agent performance.

    cloud

    54.2K  Pulls 1  Tag Updated  3 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

    479.4K  Pulls 8  Tags Updated  5 months ago

  • 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

    80.4M  Pulls 35  Tags Updated  8 months ago

  • deepseek-v3

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

    671b

    3.7M  Pulls 5  Tags Updated  1 year ago

  • deepseek-coder

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

    1.3b 6.7b 33b

    3.4M  Pulls 102  Tags Updated  2 years 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

    1.9M  Pulls 64  Tags Updated  1 year ago

  • deepseek-v2

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

    16b 236b

    687.4K  Pulls 34  Tags Updated  1 year ago

  • deepseek-llm

    An advanced language model crafted with 2 trillion bilingual tokens.

    7b 67b

    689.3K  Pulls 64  Tags Updated  2 years 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

    197.5K  Pulls 7  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

    1.2M  Pulls 5  Tags Updated  1 year ago

  • openthinker

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

    7b 32b

    912K  Pulls 15  Tags Updated  11 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

    304.2K  Pulls 9  Tags Updated  1 year ago

  • deepseek-140B/DeepSeekAI140B

    5,726  Pulls 1  Tag Updated  1 year ago

  • 3113419790/deepseek-r1

    thinking 1.5b

    16  Pulls 1  Tag Updated  3 days ago

  • f0rc3ps/deepseek-r1-32b-uncensored

    ⚠️ WARNING: All malicious actions will be punished by law.

    thinking

    992  Pulls 1  Tag Updated  2 weeks ago

  • coney_/deepseek-r1_claude-sonnet4.6

    thinking

    333  Pulls 1  Tag Updated  2 weeks ago

  • rjeffvalle/coder-pro

    Based on DeepSeek R1 because OpenCode tries to verify on the registry for tool compatibility

    tools

    100  Pulls 1  Tag Updated  1 week ago

  • richardyoung/deepseek-r1-32b-uncensored

    Advanced reasoning model with uncensored capabilities, perfect for complex problem-solving and unrestricted conversations without refusal behavior

    4,207  Pulls 1  Tag Updated  4 months ago

  • wwhyy027/deepseek-r1

    thinking 7b

    31  Pulls 1  Tag Updated  2 weeks ago

© 2026 Ollama
Blog Contact