← Back to community benchmarks

GLM-5-4.8bit

M3 Ultra (80c) · 512 GB · 4bit · 2026-03-09

Performance

32k

tokens

73.2

PP tok/s

12.3

TG tok/s

447955

TTFT (ms)

443.6

Peak mem (GB)

Hardware

Chip M3 Ultra (80c)

Memory 512 GB

GPU Cores 80

Software

oMLX v0.2.6

macOS macOS 26.2

Context 32,768

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	188.7	16.6	420.0 GB	view
4k	182.6	13.7	422.3 GB	view
8k	156.3	13.5	424.9 GB	view
16k	119.8	13.0	430.9 GB	view
32k	73.2	12.3	443.6 GB	current