Performance
1k
tokens
222.8
PP tok/s
47.5
TG tok/s
4595
TTFT (ms)
5.8
Peak mem (GB)
Hardware
Chip
M1 Max (24c)
Memory
32 GB
GPU Cores
24
Software
oMLX
v0.3.5
macOS
macOS 26.4.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 222.8 | 47.5 | 5.8 GB | current |
| 4k | 235.6 | 44.6 | 6.5 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 47.5 | 1.00× |
| 2× | 52.9 | 1.11× |
| 4× | 54.9 | 1.16× |