← Back to community benchmarks

GLM-OCR

M3 Max (40c) · 128 GB · bf16 · 2026-03-09
Performance
32k
tokens
3,656
PP tok/s
61.3
TG tok/s
8964
TTFT (ms)
4.6
Peak mem (GB)
Hardware
Chip M3 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.2.6
macOS macOS 26.3
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
32k 3,656 61.3 4.6 GB current
64k 2,041 45.4 6.8 GB view