← Back to community benchmarks

1e20fd8d42056f870933bf98ca6211024744f7ec

M4 Max (40c) · 128 GB · 4bit · 2026-04-17
Performance
1k
tokens
1,460
PP tok/s
396.3
TG tok/s
701
TTFT (ms)
19.9
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.6
macOS macOS 15.4.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,460 396.3 19.9 GB current
4k 847.3 108.5 20.0 GB view