← Back to community benchmarks
GLM-OCR-8bit
Performance
8k
tokens
1,416
PP tok/s
25.1
TG tok/s
5785
TTFT (ms)
4.4
Peak mem (GB)
Hardware
Chip
M3 (8c)
Memory
16 GB
GPU Cores
8
Software
oMLX
v0.3.6
macOS
macOS 26.4.1
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,838 | 43.0 | 4.2 GB | view |
| 4k | 1,691 | 27.5 | 4.2 GB | view |
| 8k | 1,416 | 25.1 | 4.4 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 43.0 | 1.00× |
| 2× | 54.4 | 1.27× |
| 4× | 103.0 | 2.40× |
| 8× | 134.6 | 3.13× |