Builds / 4x Nvidia GB10 (unified, DGX Spark)
4x DGX Spark: MiniMax M3.1 Flash NVFP4 on vLLM TP4, 22 tok/s chat (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)
- 4x Nvidia GB10 (unified, DGX Spark)
- VRAM / unified memory (GB)
- 512
- CPU
- Nvidia GB10 Grace (Arm) per node
Amazon · eBay (used) · Newegg - Motherboard
- not stated
- RAM
- 128 GB LPDDR5X unified per Spark (512 GB total)
- PSU
- not stated
- Other
- 4 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 | NVFP4 + DSpark | vLLM TP4, 4 nodes, 1 stream | 22 | not stated | ⚡ spec-decode (DSpark)📏 Single-stream chat decode as published in Tech2wild's recipe README (short chat prompt, single user). |
Numbers by Tech2wild (tonyd2wild); short chat prompt, single user. 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: MIT.
Source: https://github.com/tonyd2wild/MiniMax-M3.1-Flash-TP4-DGX-Sparks
https://github.com/tonyd2wild/MiniMax-M3.1-Flash-TP4-DGX-Sparks/blob/main/README.md
https://github.com/tonyd2wild/MiniMax-M3.1-Flash-TP4-DGX-Sparks/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 4x DGX Spark (GB10) run MiniMax M3.1 Flash?