← Back to community benchmarks

Q36OP47

M5 Max (40c) · 128 GB · 8bit · 2026-04-25
Performance
1k
tokens
2,094
PP tok/s
97.5
TG tok/s
489
TTFT (ms)
35.4
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
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 2,094 97.5 35.4 GB current
4k 3,591 94.0 36.2 GB view
Batching Results
Batch Size TG tok/s Speedup
97.5 1.00×
159.2 1.63×
234.7 2.41×