Check my GPU

LLMs ·

DeepSeek V4 Flash (284B-A13B)

Parameters
304B (13.0B active)
Architecture
Mixture of experts
Max context
1,024K tokens
License
mit
Released
2026-07

How to run it

Ollama

Ollama only offered this as a cloud model, and has since retired it. To run it locally, use the GGUF files below with llama.cpp or LM Studio.

Quantized files · GGUF

Works in LM Studio, llama.cpp, Jan and Ollama. No sign-in needed.

huggingface.co/unsloth/DeepSeek-V4-Flash-0731-GGUF (opens in a new tab)

ollama run hf.co/unsloth/DeepSeek-V4-Flash-0731-GGUF

Original weights · Hugging Face

Full-precision files from DeepSeek, for fine-tuning, vLLM, Transformers.

huggingface.co/deepseek-ai/DeepSeek-V4-Flash-0731 (opens in a new tab)

No sign-in needed.

Links checked 5 days ago against Hugging Face, Ollama and GitHub.

Memory needed

Weights plus KV cache and runtime overhead. Leave a little extra free for the operating system and other apps.

KV cache: compressed KV cache (single 512-value head per layer); estimate treats it like a latent cache.

Quantization Quality Weights Total at 8K context Total at 32K context Download
Q2_K Low 122 GB 123 GB 124 GB GGUF (UD-Q2_K_XL) · folder (opens in a new tab)
Q3_K_M Low 149 GB 150 GB 151 GB GGUF · folder (opens in a new tab)
Q4_K_M Good 186 GB 187 GB 188 GB GGUF (UD-Q4_K_XL) · folder (opens in a new tab)
Q5_K_M High 216 GB 217 GB 218 GB GGUF files (opens in a new tab)
Q6_K High 249 GB 250 GB 251 GB GGUF files (opens in a new tab)
Q8_0 Very high 322 GB 323 GB 324 GB GGUF (opens in a new tab)
F16 Full 608 GB 609 GB 610 GB GGUF · folder (opens in a new tab) Original weights (opens in a new tab)

Best hardware for DeepSeek V4 Flash (284B-A13B)

Grade · points Hardware Quant Memory Speed Fit
91 ptsExcellent (S) · 91 of 100 points: Model quality 40.2/45, Memory fit 25.0/25, Speed 13.7/15, Memory use 13.1/15 Apple M3 Ultra (512 GB) Q4_K_M 217 GB / 384 GB 33.3 tok/s Runs well
89 ptsExcellent (S) · 89 of 100 points: Model quality 35.5/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15 Apple M3 Ultra (256 GB) Q3_K_M 165 GB / 192 GB 43.0 tok/s Tight fit
83 ptsGreat (A) · 83 of 100 points: Model quality 29.6/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15 Apple M2 Ultra (192 GB) Q2_K 134 GB / 144 GB 53.4 tok/s Tight fit

Check it on your own hardware

Estimates come from published hardware specs and our open formulas, not from running the model on your machine. Real speed varies with runtime, drivers and settings. Numbers marked “Measured” come from a linked benchmark.