← Back to community benchmarks
GLM-OCR
Performance
4k
tokens
2,474
PP tok/s
65.1
TG tok/s
1656
TTFT (ms)
2.9
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.2.8
macOS
macOS 26.3.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 2,745 | 77.4 | 2.6 GB | view |
| 4k | 2,474 | 65.1 | 2.9 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 77.4 | 1.00× |
| 2× | 95.7 | 1.24× |
| 4× | 169.7 | 2.19× |