← Back to community benchmarks

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

M4 Max (40c) · 128 GB · 4bit · 2026-05-23
Performance
16k
tokens
227.2
PP tok/s
25.3
TG tok/s
72118
TTFT (ms)
19.1
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.9
macOS macOS 26.5
Context 16,384