4× DGX Spark
22.2tok/sEveryday
1 request, short prose prompt, with DSpark (per recipe) Source
Intelligenceno independent value
- License unclear
Local AI · Recipe · 1× DGX Spark
MiniMax-M3.1-Flash EXL3 2.15 bpw with vLLM on 1× DGX Spark
MiniMax-M3.1-Flash EXL3 2.15 bpw with vLLM on 1× DGX Spark: 24.4 tok/s according to github.com (dataset as of Nov 3, 2026).
by vcruz305
Intelligence (original model) · Artificial Analysisno independent value
≤ 3 bit: quantization may cost quality
Engine
- Engine
- vLLM (vllm/vllm-openai:minimax-m31-flash, Digest 86f582da) + vllm-exl3 Fork 41fdb7d + exllamav3 Fork fdd7736, DSpark k=4
- Quantization
- EXL3 SAGE 2.15bpw, q4-KV (nvfp4-Layout), fp8 Indexer-/Draft-KV
- Model family
- MiniMax-M3.1-Flash
- Context
- 49,152
- Parameters
- 428B MoE / 23B aktiv (lt. HF-Card)
- Creator
- vcruz305
- GitHub stars
- 6
- Repo updated
- Oct 24, 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
- 1 × NVIDIA DGX Spark (GB10)
- Weights
- Main weightsvcruz305/MiniMax-M3.1-Flash-EXL3-SAGE-2.15bpw other
- BaseMiniMaxAI/MiniMax-M3.1-Flash other
- Engine
- vLLM (vllm/vllm-openai:minimax-m31-flash, Digest 86f582da) + vllm-exl3 Fork 41fdb7d + exllamav3 Fork fdd7736, DSpark k=4
- Context
- 49,152 tokens
Notes
What matters before you rebuild it.
- ≤ 3 bit: quantization may cost qualityAt 3 bit and below the model may answer noticeably worse than the original. The intelligence number refers to the original.
- Custom kernel required
- 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
1× DGX Spark
71.8tok/sEveryday
1 request, prose prompt (sampled, thinking off), with LiLiCorr (per recipe) Source
Intelligenceno independent value
- ≤ 3 bit: quantization may cost quality
- Custom kernel required
- License unclear
1× DGX Spark
60.3tok/sEveryday
1 request, prose prompt (essay), context 2k, no drafter (per recipe) Source
Intelligenceno independent value
- Custom kernel required
1× DGX Spark
59.4tok/sEveryday
1 request, chat prompt (20 prompts, thinking off), no drafting (default profile) Source
Intelligenceno independent value
- Custom kernel required
1× DGX Spark
58.3tok/sEveryday
1 request, prose prompt, with DFlash2 (per recipe) Source
Intelligence34with thinkingno thinking 20
- 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.