---
type: "Article"
title: "MiniMax-M3.1-Flash EXL3 2.15 bpw with vLLM (EXL3 plugin) on 2× DGX Spark"
description: "MiniMax-M3.1-Flash EXL3 2.15 bpw with vLLM (EXL3 plugin) on 2× DGX Spark: recipe by tonyd2wild with speed, condition and source for every number, weights and license."
resource: "https://www.contextstudios.ai/local-ai/tonyd2wild--minimax-m3.1-flash-exl3-sage-2.15bpw-tp2-2x-dgx-spark"
language: "en"
generated:
  by: "process:contextstudios-md/1"
  at: "2026-11-11T03:30:21.387Z"
status: "stable"
---

# MiniMax-M3.1-Flash EXL3 2.15 bpw with vLLM (EXL3 plugin) on 2× DGX Spark

MiniMax-M3.1-Flash EXL3 2.15 bpw with vLLM (EXL3 plugin) on 2× DGX Spark: 19.8 tok/s according to github.com (dataset as of Nov 3, 2026).

- Creator: [tonyd2wild](https://www.contextstudios.ai/local-ai/creators/tonyd2wild.md)
- Engine: vLLM + vllm-exl3 plugin (vcruz305 image/forks, pin 41fdb7d) + 2 TP2 patches
- Quantization: EXL3 SAGE 2.15 bpw + q4 KV (fp8 indexer/draft KV)
- Model family: MiniMax-M3.1-Flash
- Hardware: dgx-spark x2
- Context: 300000

## All numbers

- 19.8 tok/s (Everyday; Everyday, 1 request, prose prompt, with DSpark (per recipe)) — [source](https://github.com/tonyd2wild/MiniMax-M3.1-Flash-EXL3-TP2-2x-DGX-Spark#results-2026-10-24)
- decode_tps: 19.8 (1 request) — [source](https://github.com/tonyd2wild/MiniMax-M3.1-Flash-EXL3-TP2-2x-DGX-Spark#results-2026-10-24)
- decode_tps: 31.7 (1 request) — [source](https://github.com/tonyd2wild/MiniMax-M3.1-Flash-EXL3-TP2-2x-DGX-Spark#results-2026-10-24)
- decode_tps: 39.4 (1 request) — [source](https://github.com/tonyd2wild/MiniMax-M3.1-Flash-EXL3-TP2-2x-DGX-Spark#results-2026-10-24)
- prefill_tps: 527 (1 request) — [source](https://github.com/tonyd2wild/MiniMax-M3.1-Flash-EXL3-TP2-2x-DGX-Spark#results-2026-10-24)
- ttft_ms: 670 (1 request) — [source](https://github.com/tonyd2wild/MiniMax-M3.1-Flash-EXL3-TP2-2x-DGX-Spark#results-2026-10-24)

## Weights

- [vcruz305/MiniMax-M3.1-Flash-EXL3-SAGE-2.15bpw](https://huggingface.co/vcruz305/MiniMax-M3.1-Flash-EXL3-SAGE-2.15bpw) (main, other)
- [MiniMaxAI/MiniMax-M3.1-Flash](https://huggingface.co/MiniMaxAI/MiniMax-M3.1-Flash) (base, other)

[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)

## Related

- [Local AI on your hardware.](https://www.contextstudios.ai/local-ai.md)