Performance
1k
tokens
65.6
PP tok/s
12.5
TG tok/s
15606
TTFT (ms)
14.3
Peak mem (GB)
Hardware
Chip
M1 Max (24c)
Memory
64 GB
GPU Cores
24
Software
oMLX
v0.3.9rc1
macOS
macOS 26.2
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 65.6 | 12.5 | 14.3 GB | current |
| 4k | 51.8 | 9.2 | 15.6 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 12.5 | 1.00× |
| 2× | 10.4 | 0.83× |
| 4× | 13.3 | 1.06× |