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

    412K  Pulls 2  Tags Updated  1 month 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

    369.9K  Pulls 2  Tags Updated  2 weeks ago

  • lcz2026/Qwen3.5-DeepSeek-V4-9B-Flash

    88  Pulls 1  Tag Updated  4 days ago

  • 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.

    373  Pulls 1  Tag Updated  2 weeks ago

  • rafw007/deepseek-v4-flash-fast

    DeepSeek-V4-Flash-Fast is a custom agent build based on DeepSeek-V4-Flash (Open Weights, Apache-2.0, MoE, ~285B total / ~20B active). Weights in low-bit quantization for fully CPU-only deployment:

    273  Pulls 1  Tag Updated  3 weeks ago

  • pdurugyan/qwen3.5-9b-deepseek-v4-flash-Q4_K_M-v_2

    Jackrong/Qwen3.5-9B-DeepSeek-V4-Flash - is an efficient reasoning model distilled using high-quality data from DeepSeek-V4. + vision. ollama v.0.30.0-rc20 +

    vision tools thinking

    5,875  Pulls 1  Tag Updated  3 months ago

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

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

    tools thinking

    3,588  Pulls 1  Tag Updated  3 months ago

  • pdurugyan/qwen3.5-9b-deepseek-v4-flash-Q4_K_M

    Jackrong/Qwen3.5-9B-DeepSeek-V4-Flash - is an efficient reasoning model distilled using high-quality data from DeepSeek-V4.

    tools thinking

    2,399  Pulls 1  Tag Updated  3 months ago

  • aratan/qwen3.7-35b-q4

    No Oficial 29 t/s en 8 VRAM - Calidad a escala fronteriza como GPT-5.5, DeepSeek-V4-pro y Kimi-K2.6.

    vision tools

    938  Pulls 1  Tag Updated  1 month ago

  • kenevo/DeepSeek-V4-Flash-UD-Q4_K_XL

    To run DeepSeek-V4-Flash in full precision lossless, run Q4 (UD-Q4_K_XL), It is 155GB. vision tools thinking

    661  Pulls 1  Tag Updated  1 month ago

  • quochuynguyenle69/openquote-1.0

    A customized DeepSeek-V4-Pro

    cloud

    17  Pulls 1  Tag Updated  1 week ago

  • kenevo/DeepSeek-V4-Flash-UD-IQ1_S

    To run DeepSeek-V4-Flash in full precision lossless, run IQ1 (UD-IQ1_S), It is 82GB. vision tools thinking

    270  Pulls 1  Tag Updated  1 month ago

  • seansandwich22/deepseekV4

    ollama run hf.co/unsloth/DeepSeek-V4-Flash-GGUF:UD-Q4_K_XL

    tools

    278  Pulls 1  Tag Updated  1 month 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

    127  Pulls 1  Tag Updated  1 month 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

    1,404  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

    968  Pulls 4  Tags Updated  1 year ago

  • haghiri/DeepSeek-V3-0324

    Merged Unsloth's Dynamic Quantization

    1,382  Pulls 1  Tag Updated  1 year ago

  • mo7art/DeepSeek-V3-0324

    Latest DeepSeek_V3 model Q4

    249  Pulls 1  Tag Updated  1 year ago

  • LONGTIMEDEVELOPERS/deepseek-v4-pro-qwen_russian

    115  Pulls 1  Tag Updated  2 months ago

© 2026 Ollama
Blog Support