← Back to community benchmarks

Qwen3.6-27B-UD

M5 Pro (20c) · 64 GB · 4bit · 2026-06-17
Performance
4k
tokens
371.9
PP tok/s
11.3
TG tok/s
11014
TTFT (ms)
26.6
Peak mem (GB)
Hardware
Chip M5 Pro (20c)
Memory 64 GB
GPU Cores 20
Software
oMLX v0.4.4
macOS macOS 27.0
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 318.2 11.5 25.2 GB view
4k 371.9 11.3 26.6 GB current
Batching Results
Batch Size TG tok/s Speedup
11.5 1.00×
14.5 1.26×
23.4 2.03×
32.4 2.82×