FR
Réserver un appel

Local AI · Recipe · 4× DGX Spark

MiMo-V2.6-Flash-MOPD with SparkRing on 4× DGX Spark

MiMo-V2.6-Flash-MOPD with SparkRing on 4× DGX Spark: 62.8 tok/s according to github.com (dataset as of Sep 29, 2026).

by fujitsupolycom

62.8tok/sEveryday

1 request, decode at 16K context (profile table), thinking on

Source: github.com
Intelligence (original model) · Artificial Analysisno independent value
Instructions in the README Repo

Engine

Engine
vLLM (local-inference-lab Fork) via SparkRing (switchless NCCL ueber ConnectX-7)
Quantization
Stock-Checkpoint (Xiaomi MiMo)
Model family
MiMo-V2.6-Flash-MOPD
Context
—
Parameters
310,8 GB Safetensors
Creator
fujitsupolycom
GitHub stars
91
Repo updated
Oct 6, 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

  • Everyday (decode)62.8 tok/scontext 16K · 1 Nutzer, je 16K Kontext; Thinking on Source 

Decode · parallel requests

Sums over all streams are marked; per request it is correspondingly less.

  • 16 parallel requests317 tok/sPeak (decode) · context 16K · Thinking on Source 

Prefill by context

What you need

Hardware
4 × NVIDIA DGX Spark (GB10)
Engine
vLLM (local-inference-lab Fork) via SparkRing (switchless NCCL ueber ConnectX-7)

Notes

What matters before you rebuild it.

  • Custom kernel required

Sources

Related recipes

← Back to overview

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.

See the AI workshopBack to overview