← Back to community benchmarks

Qwen3.6-27B-oQ4-mtp

M5 Max (40c) · 128 GB · 4bit · 2026-05-11
Performance
8k
tokens
834.5
PP tok/s
43.5
TG tok/s
9817
TTFT (ms)
19.2
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 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 743.3 46.4 16.8 GB view
4k 876.8 45.3 18.2 GB view
8k 834.5 43.5 19.2 GB current
16k 744.5 41.7 20.7 GB view
32k 679.8 39.0 23.7 GB view