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
MiMo-V2.6-Flash 309B-A15B MXFP4 with vLLM on 2× DGX Spark: 53.3 tok/s according to github.com (dataset as of Nov 3, 2026).
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
- 45
- Repo updated
- Oct 4, 2026
Measurements
Every sourced value of this recipe, each with its condition and source. Bars relative to the largest value in the group.
Decode · 1 request
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
4× DGX Spark
59.8tok/sMixed
1 request, mixed prompt set, with DFlash (per recipe) Source
Intelligenceno independent value
- Custom kernel required
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
89.3tok/sEveryday
1 request, prose prompt, with MTP (per recipe) Source
Intelligenceno independent value
- Custom kernel required
- License unclear
2× DGX Spark
74tok/sEveryday
1 request, prose prompt (long story), thinking off, with MTP Source
Intelligence40with thinking
- Custom kernel required
- License unclear
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.