← Back to community benchmarks

model

M4 Max (40c) · 128 GB · 8bit · 2026-03-09
Performance
1k
tokens
216.7
PP tok/s
14.9
TG tok/s
4724
TTFT (ms)
28.4
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.2.6
macOS macOS 26.3.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 216.7 14.9 28.4 GB current
4k 221.7 14.5 28.7 GB view
Batching Results
Batch Size TG tok/s Speedup
14.9 1.00×
23.8 1.60×
25.3 1.70×