← Back to community benchmarks

GLM-OCR

M4 (10c) · 16 GB · bf16 · 2026-03-10
Performance
1k
tokens
2,437
PP tok/s
66.9
TG tok/s
420
TTFT (ms)
2.6
Peak mem (GB)
Hardware
Chip M4 (10c)
Memory 16 GB
GPU Cores 10
Software
oMLX v0.2.6
macOS macOS 26.3.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 2,437 66.9 2.6 GB current
4k 2,218 57.2 2.9 GB view
Batching Results
Batch Size TG tok/s Speedup
66.9 1.00×
81.8 1.22×
135.0 2.02×