← Back to community benchmarks

GLM-5.2

M3 Ultra (80c) · 512 GB · 4bit · 2026-07-25
Performance
16k
tokens
177.1
PP tok/s
16.9
TG tok/s
92510
TTFT (ms)
395.5
Peak mem (GB)
Hardware
Chip M3 Ultra (80c)
Memory 512 GB
GPU Cores 80
Software
oMLX v0.5.0
macOS macOS 26.5.2
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 195.1 18.6 390.9 GB view
4k 212.5 17.5 392.9 GB view
8k 190.8 17.3 394.5 GB view
16k 177.1 16.9 395.5 GB current
32k 172.9 16.9 397.9 GB view
64k 111.1 15.9 399.5 GB view