← Back to community benchmarks

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

M4 (10c) · 32 GB · 4bit · 2026-05-22
Performance
32k
tokens
53.8
PP tok/s
5.5
TG tok/s
609245
TTFT (ms)
21.6
Peak mem (GB)
Hardware
Chip M4 (10c)
Memory 32 GB
GPU Cores 10
Software
oMLX v0.3.9
macOS macOS 26.5
Context 32,768