2× DGX Spark
35tok/sEveryday
1 request, prose prompt, with EAGLE Source
Intelligenceno independent value
- Experimental
Local AI · Recipe · 2× DGX Spark
MiMo-V2.6-Flash 309B-A15B MXFP4 with vLLM on 2× DGX Spark
by tonyd2wild
Intelligence (original model) · Artificial Analysisno independent value
Engine
- Engine
- vLLM
- Quantization
- MXFP4 experts (marlin) + FP8 KV
- Model family
- MiMo-V2.6-Flash
- Context
- 300,000
- Parameters
- 309B / 15B active (lt. Mia-README)
- Creator
- tonyd2wild
- GitHub stars
- 43
- Repo updated
- Sep 24, 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
- 2 × NVIDIA DGX Spark (GB10)
- Weights
- Main weightsXiaomiMiMo/MiMo-V2.6-Flash-RL MIT
- Engine
- vLLM
- Context
- 300,000 tokens
Notes
What matters before you rebuild it.
- Custom kernel required
Sources
Related recipes
1× RTX PRO 6000
184tok/sPeak
1 request, best value reported by source, context 64k Source
Intelligenceno independent value
- ≤ 3 bit: quantization may cost quality
- Custom kernel required
2× DGX Spark
no documented speed
Intelligenceno independent value
- Custom kernel required
2× DGX Spark
54.4tok/sEveryday
1 request, prose prompt, with MTP (per recipe) Source
Intelligence40with thinking
- Access on request
- License unclear
2× DGX Spark
36.1tok/sEveryday
1 request, prose prompt, with DFlash2 (per recipe) Source
Intelligence42with thinking
- ≤ 3 bit: quantization may cost quality
- Custom kernel required
- Non-commercial
- License unclear
2× DGX Spark
33.2tok/sEveryday
1 request, prose prompt, with DSpark (per recipe) Source
Intelligenceno independent value
- 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.