← Back to community benchmarks
GLM-OCR
Performance
1k
tokens
3,344
PP tok/s
218.4
TG tok/s
306
TTFT (ms)
2.9
Peak mem (GB)
Hardware
Chip
M1 Ultra (64c)
Memory
128 GB
GPU Cores
64
Software
oMLX
v0.2.9
macOS
macOS 26.3.1
Context
1,024
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 218.4 | 1.00× |
| 2× | 163.2 | 0.75× |
| 4× | 244.3 | 1.12× |