Builds / 2x Nvidia GB10 (unified, DGX Spark)
2x DGX Spark: MiniMax M3.1 Flash EXL3 SAGE 2.15 bpw on vLLM-EXL3 TP2, 19.8 tok/s prose (Tech2wild)
Last updated:
Source: github.com ↗More source: github.com ↗📏 How measured: reported by the original source; RigBase re-checked the numbers at that source
- GPU(s)
- 2x Nvidia GB10 (unified, DGX Spark)
- VRAM / unified memory (GB)
- 256
- CPU
- Nvidia GB10 Grace (Arm) per node
Amazon · eBay (used) · Newegg - Motherboard
- not stated
- RAM
- 128 GB LPDDR5X unified per Spark (256 GB total)
- PSU
- not stated
- Other
- 2 NVIDIA DGX Sparks, multi-node
- Reported total cost
- not stated
- Power
- not stated
Measured speed (generation tokens/sec)
| Model | Quant | Engine | tok/s | Prompt processing (tok/s) | Details |
|---|---|---|---|---|---|
| MiniMax M3.1 Flash | EXL3 SAGE 2.15 bpw + DSpark | vLLM-EXL3 TP2, 2 nodes, 1 stream | 19.8 | not stated | ⚡ spec-decode (DSpark)context: 300K📏 Single-stream prose decode as published in Tech2wild's recipe README (vcruz305 MiniMax-M3.1-Flash-EXL3 pack). |
| MiniMax M3.1 Flash | EXL3 SAGE 2.15 bpw + DSpark | vLLM-EXL3 TP2, 2 nodes, 1 stream | 30.4 | not stated | ⚡ spec-decode (DSpark)context: 300K📏 Single-stream code decode as published in the same Tech2wild README. |
Numbers by Tech2wild (tonyd2wild); vcruz305 MiniMax-M3.1-Flash-EXL3 pack. RigBase read the GitHub README on 2026-10-28 and checked each figure against the text. RigBase did not re-run it. Speculative decoding (MTP/DFlash/DSpark) inflates predictable text; these rows prefer prose/code over counting peaks. Recipe license: NOASSERTION (custom/unclear on API).
Source: https://github.com/tonyd2wild/MiniMax-M3.1-Flash-EXL3-TP2-2x-DGX-Spark
https://github.com/tonyd2wild/MiniMax-M3.1-Flash-EXL3-TP2-2x-DGX-Spark/blob/main/README.md
https://github.com/tonyd2wild/MiniMax-M3.1-Flash-EXL3-TP2-2x-DGX-Spark/blob/main/README.md
Blank fields = not stated in the source. We never estimate build data; GPU street prices above are separately sourced and dated.
Rent before you buy: try this model on a cloud GPU for a few dollars first: Runpod (referral link; sign up with Google to get the new-user bonus)
Quick answers: Can 2x DGX Spark (GB10) run MiniMax M3.1 Flash?