← Back to community benchmarks

Qwen3.6-27B-UD

M3 Max (40c) · 64 GB · 4bit · 2026-04-26
Performance
16k
tokens
187.5
PP tok/s
12.4
TG tok/s
87378
TTFT (ms)
28.5
Peak mem (GB)
Hardware
Chip M3 Max (40c)
Memory 64 GB
GPU Cores 40
Software
oMLX v0.3.7
macOS macOS 26.4.1
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 199.7 44.6 28.9 GB view
4k 179.9 14.4 26.6 GB view
8k 201.3 13.7 27.3 GB view
16k 187.5 12.4 28.5 GB current