← Back to community benchmarks

Qwen3.6-27B-UD

M5 Max (40c) · 128 GB · 4bit · 2026-04-28
Performance
32k
tokens
702.5
PP tok/s
18.0
TG tok/s
46642
TTFT (ms)
31.0
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.7
macOS macOS 26.4.1
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 653.7 107.7 28.9 GB view
4k 674.2 21.0 26.6 GB view
8k 897.1 20.5 27.3 GB view
16k 784.0 19.4 28.5 GB view
32k 702.5 18.0 31.0 GB current