Local AI · Recipe · 4× DGX Spark

GLM-5.3 743B NVFP4 with vLLM on 4× DGX Spark

by tonyd2wild

53.3tok/sPeak

1 request, JSON prompt

Source: github.com
Intelligence (original model) · Artificial Analysis45with thinking

Engine

Engine
vLLM 0.23.1rc1.dev190
Quantization
Int4-Int8Mix + NVFP4 KV
Model family
GLM-5.3
Context
270,000
Parameters
743B total / ~40B active
Creator
tonyd2wild
GitHub stars
16
Repo updated
Sep 22, 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
4 × NVIDIA DGX Spark (GB10)
Engine
vLLM 0.23.1rc1.dev190
Context
270,000 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.