← Back to community benchmarks

Qwen3.6-27B-oQ4-mtp

M5 Max (40c) · 128 GB · 4bit · 2026-05-07
Performance
1k
tokens
749.2
PP tok/s
46.1
TG tok/s
1367
TTFT (ms)
16.8
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.9.dev1
macOS macOS 26.4.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 749.2 46.1 16.8 GB current
4k 851.5 44.4 18.2 GB view
8k 800.4 42.7 19.2 GB view
16k 700.5 40.6 20.7 GB view
32k 658.2 34.6 23.7 GB view