Ollama
Models Docs Pricing
Sign in Download
Models Download Docs Pricing Sign in
⇅
deepseek V4 · 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

    56.7K  Pulls 1  Tag Updated  2 weeks ago

  • deepseek-v4-pro

    DeepSeek-V4-Pro is a frontier Mixture-of-Experts model with a 1M-token context window and three reasoning modes.

    tools thinking cloud

    47.2K  Pulls 1  Tag Updated  1 week 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

    2.5M  Pulls 64  Tags Updated  1 year ago

  • zerocopia/deepseek-v4-flash

    tools thinking cloud

    106  Pulls 1  Tag Updated  2 weeks 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

    1,371  Pulls 5  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

    952  Pulls 4  Tags Updated  1 year ago

  • second_constantine/deepseek-coder-v2

    This is a brand new Mixture of Export (MoE) model from DeepSeek, specializing in coding instructions. (quantized IQ4_XS)

    tools 16b

    11.1K  Pulls 3  Tags Updated  3 months ago

  • mannix/deepseek-coder-v2-lite-instruct

    An open-source Mixture-of-Experts code language model that achieves performance comparable to GPT4-Turbo in code-specific tasks.

    6,452  Pulls 23  Tags Updated  1 year ago

  • xiaowangge/deepseek-v3-qwen2.5

    This model has been developed based on DistilQwen2.5-DS3-0324-Series.

    tools 32b

    1,175  Pulls 7  Tags Updated  1 year ago

  • 8b-wraith/deepseek-v3-0324

    deepseek-v3-0324-Quants. - Q2_K is the lowest here - quantized = round((original - zero_point) / scale)

    1,115  Pulls 1  Tag Updated  1 year ago

  • networkjohnny/deepseek-coder-v2-lite-base-q4_k_m-gguf

    This model was converted to GGUF format from deepseek-ai/DeepSeek-Coder-V2-Lite-Base using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model.

    tools

    1,021  Pulls 1  Tag Updated  1 year ago

  • sunny-g/deepseek-v3-0324

    dynamic quants from unsloth, merged

    293  Pulls 1  Tag Updated  1 year ago

  • valerybugakov/deepseek-coder-7b-base-v1.5.q4_k

    179  Pulls 1  Tag Updated  2 years ago

  • lucataco/deepseek-v3-64k

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

    21  Pulls 1  Tag Updated  1 year ago

  • haghiri/DeepSeek-V3-0324

    Merged Unsloth's Dynamic Quantization

    1,380  Pulls 1  Tag Updated  1 year ago

  • mo7art/DeepSeek-V3-0324

    Latest DeepSeek_V3 model Q4

    249  Pulls 1  Tag Updated  1 year ago

© 2026 Ollama
Blog Contact