Performance
1k
tokens
119.0
PP tok/s
14.3
TG tok/s
8603
TTFT (ms)
23.0
Peak mem (GB)
Hardware
Chip
M4 Pro (20c)
Memory
64 GB
GPU Cores
20
Software
oMLX
v0.3.9.dev2
macOS
macOS 26.4.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 119.0 | 14.3 | 23.0 GB | current |
| 4k | 107.3 | 13.6 | 24.4 GB | view |