2× DGX Spark
35tok/sEveryday
1 request, prose prompt, with EAGLE Source
Intelligenceno independent value
- Experimental
Local AI · Recipe · 4× DGX Spark
MiMo-V2.6-Flash 311B FP8 with vLLM on 4× DGX Spark
MiMo-V2.6-Flash 311B FP8 with vLLM on 4× DGX Spark: 59.8 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
- Original-Checkpoint (FP8), FP8 KV
- Model family
- MiMo-V2.6-Flash
- Context
- 500,000
- Parameters
- ~311B MoE
- 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
Prefill by context
What you need
- Hardware
- 4 × NVIDIA DGX Spark (GB10)
- Weights
- Main weightsXiaomiMiMo/MiMo-V2.6-Flash-RL MIT
- Engine
- vLLM
- Context
- 500,000 tokens
Notes
What matters before you rebuild it.
- Custom kernel required
Sources
- github.com/tonyd2wild/MiMo-V2.6-Flash-DGX-Spark-Recipe/blob/main/results/tp4/bench-tp4-gmu85-c1clean.md
- github.com/tonyd2wild/MiMo-V2.6-Flash-DGX-Spark-Recipe/blob/main/results/tp4/bench-tp4-gmu85-base.md
- github.com/tonyd2wild/MiMo-V2.6-Flash-DGX-Spark-Recipe/blob/main/results/tp4/bench-tp4-gmu85-hiconc.md
- github.com/tonyd2wild/MiMo-V2.6-Flash-DGX-Spark-Recipe/blob/main/README.md#L127
Related recipes
2× DGX Spark
53.3tok/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
4× DGX Spark
87.7tok/sEveryday
1 request, prose prompt, with DSpark (per recipe) Source
Intelligence40with thinkingno thinking 25
4× DGX Spark
78tok/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.