1 request, prose prompt, with DSpark (per recipe) Source
Local AI · Recipe · 3× DGX Spark
DeepSeek-V4.1-Flash 763B MXFP4 with SGLang on 3× DGX Spark
by MiaAI-Lab
1 request, prose prompt, with MTP/EAGLE (spekulativ, ~59 ms/step) (per recipe)
Source: github.comEngine
- Engine
- SGLang
- Quantization
- native MXFP4 experts + FP8 dense
- Model family
- DeepSeek-V4.1-Flash
- Context
- 262,144
- Parameters
- ~763B
- Creator
- MiaAI-Lab
- GitHub stars
- 172
- Repo updated
- Sep 25, 2026
Measurements
Every sourced value of this recipe, each with its condition and source. Bars relative to the largest value in the group.
No sourced measurements for this recipe.
What you need
- Hardware
- 3 × NVIDIA DGX Spark (GB10)
- Weights
- Main weightsdeepseek-ai/DeepSeek-V4.1-Flash MIT
- Engine
- SGLang
- Context
- 262,144 tokens
Notes
What matters before you rebuild it.
- Custom kernel required
Sources
Related recipes
1 request, prose prompt, context 32788, with DSPARK Source
1 request, prose prompt, with DSpark (per recipe) Source
1 request, prose prompt, with DSpark (per recipe) Source
- ≤ 3 bit: quantization may cost quality
- Custom kernel required
1 request, prose prompt, with DSpark (per recipe) Source
- ≤ 3 bit: quantization may cost quality
- Experimental
- Custom kernel required
1 request, prose prompt, with DSpark (per recipe) Source
- Custom kernel required
Local AI in your company?
In a workshop we work out which models and which hardware fit your tasks, and build the first agent on your infrastructure.