← Back to community benchmarks

Qwen3.6-27B-MTPLX-Optimized-Speed

M5 Pro (20c) · 64 GB · 4bit · 2026-05-24
Performance
16k
tokens
451.6
PP tok/s
16.6
TG tok/s
36280
TTFT (ms)
19.1
Peak mem (GB)
Hardware
Chip M5 Pro (20c)
Memory 64 GB
GPU Cores 20
Software
oMLX v0.3.9
macOS macOS 26.5
Context 16,384