1× DGX Spark
24.4tok/sEveryday
1 request, prose prompt, with DSpark (per recipe) Source
Intelligenceno independent value
- ≤ 3 bit: quantization may cost quality
- Custom kernel required
- License unclear
Local AI · Recipe · 4× DGX Spark
MiniMax-M3.1-Flash NVFP4/MXFP8 with vLLM on 4× DGX Spark
MiniMax-M3.1-Flash NVFP4/MXFP8 with vLLM on 4× DGX Spark: 22.2 tok/s according to github.com (dataset as of Nov 3, 2026).
by tonyd2wild
Intelligence (original model) · Artificial Analysisno independent value
Engine
- Engine
- vLLM 0.1.dev23341+g8744dd2fb (vllm/vllm-openai:minimax-m31-flash-arm64-cu134)
- Quantization
- NVFP4 experts (Marlin W4A16 on GB10) + MXFP8 attention/dense, FP8 KV (official checkpoint)
- Model family
- MiniMax-M3.1-Flash
- Context
- 300,000
- Parameters
- ~428B MoE / 23B aktiv
- Creator
- tonyd2wild
- GitHub stars
- 4
- Repo updated
- Oct 23, 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
Time to first token
Shorter is better.
What you need
- Hardware
- 4 × NVIDIA DGX Spark (GB10)
- Weights
- Main weightsMiniMaxAI/MiniMax-M3.1-Flash other
- Engine
- vLLM 0.1.dev23341+g8744dd2fb (vllm/vllm-openai:minimax-m31-flash-arm64-cu134)
- Context
- 300,000 tokens
Notes
What matters before you rebuild it.
- vision
- tool-calling
- License unclear
Sources
Related recipes
2× DGX Spark
19.8tok/sEveryday
1 request, prose prompt, with DSpark (per recipe) Source
Intelligenceno independent value
- ≤ 3 bit: quantization may cost quality
- Custom kernel required
- License unclear
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
4× DGX Spark
73tok/sEveryday
1 request, decode at 32K context (speed table, ring of four), thinking on, xhigh Source
Intelligence40with thinking
- Custom kernel required
4× DGX Spark
71tok/sEveryday
1 request, decode at 32K context (speed table, ring of four), thinking on, high Source
Intelligence40with thinkingno thinking 25
- 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.