Local AI · Recipe · 4× RTX PRO 6000

GLM-5.2 EXL3 3.5 bpw with vLLM on 4× RTX PRO 6000

GLM-5.2 EXL3 3.5 bpw with vLLM on 4× RTX PRO 6000: 74 tok/s according to huggingface.co (dataset as of Nov 3, 2026).

by brandonmusic

74tok/sPeak

1 request, best value reported by source

Source: huggingface.co
Intelligence (original model) · Artificial Analysis34with thinkingno thinking 22

Engine

Engine
vLLM verdictai custom (r17 Paket = RC)
Quantization
EXL3 TR3v4 3.5 bpw
Model family
GLM-5.2
Context
—
Creator
brandonmusic
GitHub stars
9
Repo updated
Aug 23, 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

Prefill by context

What you need

Hardware
4 × NVIDIA RTX PRO 6000 Blackwell
Engine
vLLM verdictai custom (r17 Paket = RC)

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.