Performance
1k
tokens
1,086
PP tok/s
83.0
TG tok/s
943
TTFT (ms)
89.7
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.6
macOS
macOS 26.4.1
Context
1,024