← Back to community benchmarks

GLM-OCR

M4 (10c) · 16 GB · bf16 · 2026-03-10
Performance
1k
tokens
2,958
PP tok/s
72.8
TG tok/s
346
TTFT (ms)
2.6
Peak mem (GB)
Hardware
Chip M4 (10c)
Memory 16 GB
GPU Cores 10
Software
oMLX v0.2.6
macOS macOS 26.2
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 2,958 72.8 2.6 GB current
4k 2,468 62.3 2.9 GB view
Batching Results
Batch Size TG tok/s Speedup
72.8 1.00×
95.4 1.31×
168.0 2.31×