← Back to community benchmarks

GLM-5-4.8bit

M3 Ultra (80c) · 512 GB · 4bit · 2026-03-09
Performance
16k
tokens
119.8
PP tok/s
13.0
TG tok/s
136722
TTFT (ms)
430.9
Peak mem (GB)
Hardware
Chip M3 Ultra (80c)
Memory 512 GB
GPU Cores 80
Software
oMLX v0.2.6
macOS macOS 26.2
Context 16,384
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 current
32k 73.2 12.3 443.6 GB view