Performance
4k
tokens
67.7
PP tok/s
13.9
TG tok/s
60461
TTFT (ms)
18.2
Peak mem (GB)
Hardware
Chip
M1 Max (24c)
Memory
32 GB
GPU Cores
24
Software
oMLX
v0.3.9.dev1
macOS
macOS 26.3
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 66.9 | 14.1 | 16.8 GB | view |
| 4k | 67.7 | 13.9 | 18.2 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 14.1 | 1.00× |
| 2× | 16.4 | 1.16× |
| 4× | 17.2 | 1.22× |