Local AI · Recipe · 3× DGX Spark

DeepSeek-V4.1-Flash 763B MXFP4 with SGLang on 3× DGX Spark

by MiaAI-Lab

51tok/sEveryday

1 request, prose prompt, with MTP/EAGLE (spekulativ, ~59 ms/step) (per recipe)

Source: github.com
Intelligence (original model) · Artificial Analysis40with thinkingno thinking 25

Engine

Engine
SGLang
Quantization
native MXFP4 experts + FP8 dense
Model family
DeepSeek-V4.1-Flash
Context
262,144
Parameters
~763B
Creator
MiaAI-Lab
GitHub stars
172
Repo updated
Sep 25, 2026

Measurements

Every sourced value of this recipe, each with its condition and source. Bars relative to the largest value in the group.

No sourced measurements for this recipe.

What you need

Hardware
3 × NVIDIA DGX Spark (GB10)
Engine
SGLang
Context
262,144 tokens

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.