Will this model run on your hardware?
Can I run DeepSeek: DeepSeek V4 Flash 0731 locally?
- 304B parameters (22B active, MoE)
- context up to 1024K
- licence: mit
- #10 in the AIContenders model ranking
- Weights: deepseek-ai/DeepSeek-V4-Flash-0731 · GGUF: unsloth/DeepSeek-V4-Flash-0731-GGUF
Open this page in a browser to check it against your own GPU or Mac: the tool detects your hardware locally and shows the best quantization that fits, the memory it needs and an estimated speed.
Quantizations and file sizes
| Quantization | GGUF file |
|---|---|
| UD-Q3_K_M | 128.1 GB |
Run it locally
ollama run hf.co/unsloth/DeepSeek-V4-Flash-0731-GGUF:UD-Q3_K_M
llama serve -hf unsloth/DeepSeek-V4-Flash-0731-GGUF:UD-Q3_K_M
LM Studio: open unsloth/DeepSeek-V4-Flash-0731-GGUF