Ollama
Models Docs Pricing
Sign in Download
Models Download Docs Pricing Sign in
⇅
deepseek-v3.1 · Ollama
Search for models on Ollama.
  • deepseek-v3.1

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

    tools thinking 671b

    726.9K  Pulls 7  Tags Updated  11 months 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

  • fhagenciadigital/ds-go-pro

    Senior Go & SpecKit engineering agent powered by DeepSeek-v3.1 671B, optimized for idiomatic development and deterministic BDD testing.

    cloud

    140  Pulls 1  Tag Updated  5 months ago

  • zerocopia/deepseek-v3.1

    tools thinking cloud

    38  Pulls 1  Tag Updated  4 months ago

  • ukjin/Qwen3-30B-A3B-Thinking-2507-Deepseek-v3.1-Distill

    This model is a distilled version of Qwen/Qwen3-30B-A3B-Instruct designed to inherit the reasoning and behavioral characteristics of its much larger teacher model, deepseek-ai/DeepSeek-V3.1.

    tools thinking 4b

    2,373  Pulls 2  Tags Updated  1 year ago

  • huihui_ai/deepseek-v3.1

    This is not the ablation version. DeepSeek-V3.1 is a hybrid model that supports both thinking mode and non-thinking mode.

    tools thinking 671b

    253  Pulls 3  Tags Updated  1 year ago

  • pdevine/deepseek-v3.1

    tools thinking cloud

    188  Pulls 2  Tags Updated  11 months ago

  • clore/deepseek-v3.1

    15  Pulls 1  Tag Updated  1 year ago

  • huihui_ai/deepseek-v3-pruned

    DeepSeek-V3-Pruned-Coder-411B is a pruned version of the DeepSeek-V3 reduced from 256 experts to 160 experts, The pruned model is mainly used for code generation.

    411b

    1,407  Pulls 5  Tags Updated  1 year ago

  • frob/deepseek-v4-flash-0731

    284b

    67.7K  Pulls 17  Tags Updated  3 weeks ago

  • frob/deepseek-v4-flash

    0731

    tools thinking 284b

    1,110  Pulls 17  Tags Updated  3 weeks ago

  • huihui_ai/deepseek-v3

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

    7,196  Pulls 2  Tags Updated  1 year ago

  • huihui_ai/deepseek-v3-abliterated

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

    671b

    4,108  Pulls 5  Tags Updated  1 year ago

  • milkey/deepseek-v3-UD

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

    2,064  Pulls 3  Tags Updated  1 year ago

  • lordoliver/DeepSeek-V3-0324

    DeepSeep V3 from March 2025 Merged from Unsloth's HF - 671B params - Q8_0/713 GB & Q4_K_M/404 GB

    671b

    969  Pulls 4  Tags Updated  1 year ago

  • org/deepseek-v3-fast

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

    117  Pulls 4  Tags Updated  1 year ago

  • lucataco/deepseek-v3-64k

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

    25  Pulls 1  Tag Updated  1 year ago

  • kenevo/DeepSeek-V4-Flash-UD-Q3_K_M

    To run DeepSeek-V4-Flash in full precision lossless, run Q3 (UD-Q3_K_M), It is 129 GB. vision tools thinking

    144  Pulls 1  Tag Updated  1 month ago

© 2026 Ollama
Blog Support