Ollama
Models Docs Pricing
Sign in Download
Models Download Docs Pricing Sign in
⇅
deepseek · Ollama
Search for models on Ollama.
  • deepseek-v4-flash

    DeepSeek-V4-Flash is a preview of the DeepSeek-V4 series, a Mixture-of-Experts model with 284B total parameters and 13B activated, built for efficient reasoning across a 1M-token context window.

    tools thinking cloud

    370K  Pulls 3  Tags Updated  2 weeks ago

  • deepseek-v4-pro

    DeepSeek-V4-Pro is a frontier Mixture-of-Experts model with a large context window and three reasoning modes.

    tools thinking cloud

    333.8K  Pulls 3  Tags Updated  3 days ago

  • deepseek-ocr

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

    vision 3b

    513.8K  Pulls 3  Tags Updated  9 months ago

  • deepseek-v3.1

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

    tools thinking 671b

    721.2K  Pulls 7  Tags Updated  10 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

    91.4M  Pulls 35  Tags Updated  1 year ago

  • deepseek-v3

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

    671b

    3.8M  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

    4.5M  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

    3M  Pulls 64  Tags Updated  1 year ago

  • deepseek-v2

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

    16b 236b

    1.2M  Pulls 34  Tags Updated  2 years ago

  • deepseek-llm

    An advanced language model crafted with 2 trillion bilingual tokens.

    7b 67b

    1.2M  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

    285.1K  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

    1.3M  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

    1.2M  Pulls 15  Tags Updated  1 year 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

    416.3K  Pulls 9  Tags Updated  1 year ago

  • deepseek-140B/DeepSeekAI140B

    5,806  Pulls 1  Tag Updated  1 year ago

  • erukude/cve-expert

    A fine-tuned DeepSeek-R1-70B model for CVE-worthiness review, exploit-path analysis, and JSON-only vulnerability triage.

    thinking 70b

    632  Pulls 1  Tag Updated  yesterday

  • bluehawana/deepseek-v4-flash

    DeepSeek-V4-Flash 284B MoE (13B active), single-file IQ2_M merged from AtomicChat's GGUF shards so Ollama can pull it. ~33 tok/s on a 128 GB Apple Silicon Mac. Model by DeepSeek (MIT), quantization by AtomicChat.

    39  Pulls 1  Tag Updated  yesterday

  • w2n/deepseek-v4-flash

    tools

    34  Pulls 1  Tag Updated  2 days ago

  • Beelzebub4883/deepseek-r1-1.5b

    25  Pulls 1  Tag Updated  6 days ago

  • joeho3000/deepseek-r1-70b

    thinking

    14  Pulls 1  Tag Updated  6 days ago

© 2026 Ollama
Blog Contact