Performance
4k
tokens
221.7
PP tok/s
14.5
TG tok/s
18472
TTFT (ms)
28.7
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.2.6
macOS
macOS 26.3.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 216.7 | 14.9 | 28.4 GB | view |
| 4k | 221.7 | 14.5 | 28.7 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 14.9 | 1.00× |
| 2× | 23.8 | 1.60× |
| 4× | 25.3 | 1.70× |