← Back to community benchmarks
GLM-OCR
Performance
4k
tokens
2,639
PP tok/s
64.4
TG tok/s
1552
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 | 3,007 | 75.4 | 2.6 GB | view |
| 4k | 2,639 | 64.4 | 2.9 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 75.4 | 1.00× |
| 2× | 92.2 | 1.22× |
| 4× | 145.8 | 1.93× |