← Back to community benchmarks
GLM-OCR
Performance
32k
tokens
3,618
PP tok/s
62.1
TG tok/s
9057
TTFT (ms)
4.6
Peak mem (GB)
Hardware
Chip
M3 Max (40c)
Memory
48 GB
GPU Cores
40
Software
oMLX
v0.3.5
macOS
macOS 26.5
Context
32,768