← Back to community benchmarks

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

M5 (10c) · 32 GB · 4bit · 2026-05-22
Performance
1k
tokens
198.7
PP tok/s
8.4
TG tok/s
5153
TTFT (ms)
15.8
Peak mem (GB)
Hardware
Chip M5 (10c)
Memory 32 GB
GPU Cores 10
Software
oMLX v0.3.9
macOS macOS 26.5
Context 1,024