2× DGX Spark
62.9tok/sPeak
1 request, JSON prompt Source
Intelligence25with thinking
Local AI · Recipe · 2× DGX Spark
MiMo-V2.5 310B NVFP4 with vLLM on 2× DGX Spark (1M context, with DFlash, tonyd2wild)
MiMo-V2.5 310B NVFP4 with vLLM on 2× DGX Spark (1M context, with DFlash, tonyd2wild): 37.8 tok/s according to github.com (dataset as of Nov 3, 2026).
by tonyd2wild
Engine
- Engine
- vLLM
- Quantization
- NVFP4 weights + NVFP4 KV
- Model family
- MiMo-V2.5
- Context
- 1,000,000
- Parameters
- 310B MoE
- Creator
- tonyd2wild
- GitHub stars
- 18
- Repo updated
- Jul 31, 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 weightsmitomtuna/MiMo-V2.5-0703-NVFP4 MIT
- Draft modelXiaomiMiMo/MiMo-V2.5-DFlash MIT
- otherlukealonso/MiMo-V2.5-NVFP4 MIT
- Engine
- vLLM
- Context
- 1,000,000 tokens
Notes
What matters before you rebuild it.
- Custom kernel required
Sources
Related recipes
3× DGX Spark
38.8tok/sPeak
1 request, best value reported by source Source
Intelligence25with thinking
- Superseded
2× DGX Spark
38.3tok/sPeak
1 request, mixed prompt set, context 160k Source
Intelligence25with thinking
- Experimental
- Custom kernel required
- Superseded
3× DGX Spark
38.2tok/sPeak
1 request, mixed prompt set Source
Intelligence25with thinking
- Experimental
- Custom kernel required
2× DGX Spark
31.9tok/sPeak
1 request, best value reported by source Source
Intelligence25with thinking
- Custom kernel required
2× DGX Spark
30tok/sPeak
1 request, best value reported by source Source
Intelligence25with thinking
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.