Performance
4k
tokens
3,658
PP tok/s
199.4
TG tok/s
1120
TTFT (ms)
3.2
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.2.7
macOS
macOS 26.3.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 3,785 | 213.3 | 3.1 GB | view |
| 4k | 3,658 | 199.4 | 3.2 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 213.3 | 1.00× |
| 2× | 340.0 | 1.59× |
| 4× | 403.8 | 1.89× |