← Back to community benchmarks

Qwen3.6-27B

M5 Max (40c) · 128 GB · 4bit · 2026-05-01
Performance
32k
tokens
643.8
PP tok/s
28.2
TG tok/s
50901
TTFT (ms)
22.0
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.8
macOS macOS 26.4.1
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 659.2 35.6 15.1 GB view
4k 708.9 34.6 16.5 GB view
8k 751.4 33.8 17.5 GB view
16k 737.1 31.9 19.0 GB view
32k 643.8 28.2 22.0 GB current