Will this model run on your hardware?
Can I run DeepSeek: DeepSeek V4.1 Flash locally?
- 763B parameters (49B active, MoE)
- context up to 1024K
- licence: mit
- #32 in the AIContenders model ranking
- Weights: deepseek-ai/DeepSeek-V4.1-Flash · GGUF: antirez/deepseek-v4.1-flash-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 |
|---|---|
| MXFP4 | 501.6 GB |
| Q2_K | 365.7 GB |
Run it locally
ollama run hf.co/antirez/deepseek-v4.1-flash-gguf:MXFP4
llama serve -hf antirez/deepseek-v4.1-flash-gguf:MXFP4
LM Studio: open antirez/deepseek-v4.1-flash-gguf