Ollama
Models Docs Pricing
Sign in Download
Models Download Docs Pricing Sign in
⇅
DeepSeek V3 · 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

    709.7K  Pulls 7  Tags Updated  9 months ago

  • 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

    244K  Pulls 1  Tag Updated  2 months 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

    242  Pulls 3  Tags Updated  10 months ago

  • haghiri/DeepSeek-V3-0324

    Merged Unsloth's Dynamic Quantization

    1,382  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

    1,394  Pulls 5  Tags Updated  1 year ago

  • lsm03624/deepseek-r1

    DeepSeek-R1-0528 仍然使用 2024 年 12 月所发布的 DeepSeek V3 Base 模型作为基座,但在后训练过程中投入了更多算力,显著提升了模型的思维深度与推理能力。这个8B精馏版本编程能力都爆表!

    thinking

    1,076  Pulls 1  Tag 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

    965  Pulls 4  Tags Updated  1 year ago

  • chsword/DeepSeek-V3

    tools

    686  Pulls 1  Tag Updated  1 year ago

  • mo7art/DeepSeek-V3-0324

    Latest DeepSeek_V3 model Q4

    249  Pulls 1  Tag Updated  1 year ago

  • Hanversion/MAGA-T1-Tieba-1.5B-Distill

    This is a distill model that trained from the dataset of TieBa latest. Used about 8k data and think chain from DeepSeek-V3.

    53  Pulls 1  Tag Updated  1 year ago

  • lsqtzj/DeepSeek-V3

    42  Pulls 1  Tag 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

    98  Pulls 1  Tag Updated  3 months ago

  • bhavingajjar/deepseek-v2-16b-laravel-coder

    Bob: senior PHP & Laravel assistant on DeepSeek-Coder-V2 16B. Detects Laravel 10–13 from your project, gives version-specific answers. Eloquent, APIs, queues, Sanctum, testing. Run: ollama run bhavingajjar/deepseek-v2-16b-laravel-coder

    67  Pulls 1  Tag Updated  2 weeks ago

  • ZimaBlueAI/Qwen3.5-9B-DeepSeek-V4-Flash-GGUF

    pull from hf.co/Jackrong/Qwen3.5-9B-DeepSeek-V4-Flash-GGUF

    tools thinking

    3,051  Pulls 1  Tag Updated  2 months ago

© 2026 Ollama
Blog Contact