Performance
4k
tokens
877.8
PP tok/s
59.4
TG tok/s
4666
TTFT (ms)
28.5
Peak mem (GB)
Hardware
Chip
M4 Pro (20c)
Memory
64 GB
GPU Cores
20
Software
oMLX
v0.3.6
macOS
macOS 26.4.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 743.1 | 62.0 | 27.7 GB | view |
| 4k | 877.8 | 59.4 | 28.5 GB | current |
| 64k | 475.4 | 29.9 | 33.5 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 62.0 | 1.00× |
| 2× | 92.3 | 1.49× |
| 4× | 117.5 | 1.90× |