← Back to community benchmarks

Qwen36-27B-oQ6-mtp

M4 Max (40c) · 128 GB · 6bit · 2026-05-20
Performance
16k
tokens
234.8
PP tok/s
25.6
TG tok/s
69775
TTFT (ms)
26.7
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.9rc1
macOS macOS 15.7.4
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 234.5 25.2 22.8 GB view
4k 242.6 28.1 24.2 GB view
8k 241.5 27.5 25.2 GB view
16k 234.8 25.6 26.7 GB current
32k 222.3 24.2 29.7 GB view