More
Submit build

Can 2x DGX Spark (GB10) run MiniMax M3.1 Flash?

Last updated:

Yes. Measured 30.4 tok/s generation (vLLM-EXL3 TP2, 2 nodes, 1 stream, EXL3 SAGE 2.15 bpw + DSpark; source).

Every measured result for MiniMax M3.1 Flash on 2x DGX Spark (GB10)

BuildQuant / setupEnginetok/s
2x DGX Spark: MiniMax M3.1 Flash EXL3 SAGE 2.15 bpw on vLLM-EXL3 TP2, 19.8 tok/s prose (Tech2wild)EXL3 SAGE 2.15 bpw + DSparkvLLM-EXL3 TP2, 2 nodes, 1 stream30.4source
2x DGX Spark: MiniMax M3.1 Flash EXL3 SAGE 2.15 bpw on vLLM-EXL3 TP2, 19.8 tok/s prose (Tech2wild)EXL3 SAGE 2.15 bpw + DSparkvLLM-EXL3 TP2, 2 nodes, 1 stream19.8source

Memory: 2x DGX Spark (GB10) has 256 GB. MiniMax M3.1 Flash weights are about 261.9 GB at Q4_K_M (428B params × 4.89 bits ÷ 8, before context/KV cache). Arithmetic, not a measurement; long contexts need more. Check other quants in the VRAM calculator. At Q4_K_M the weights are about 261.9 GB, more than 256 GB, so Q4_K_M doesn't fully fit without offloading part of the model to system RAM.

Speeds are decode (generation) tokens/sec as reported by each source; quant, engine and context differ, so small gaps are noise.

All measured speeds for MiniMax M3.1 Flash: best home rig for MiniMax M3.1 Flash.

MiniMax M3.1 Flash on other hardware: 4x DGX Spark (GB10) · Apple M3 Ultra

Other models measured on 2x DGX Spark (GB10): DeepSeek V4 Flash · DeepSeek V4.1 Flash · GLM-5.3 Flash · MiMo V2.6 Flash · Qwen3.8 Flash-Next

Not enough VRAM? Rent before you buy. Run MiniMax M3.1 Flash on a bigger GPU on a rented 24–96 GB cloud GPU by the hour and see the real speed before spending €1,000+. Try it on Runpod
Referral link: if you sign up with Google and add $10, Runpod gives you and RigBase bonus credit (terms). It never affects our data.