← Back to community benchmarks

Qwen3.6-27B-MXFP4-MTP

M4 Pro (16c) · 24 GB · 4bit · 2026-05-18
Performance
1k
tokens
96.8
PP tok/s
15.9
TG tok/s
10583
TTFT (ms)
15.9
Peak mem (GB)
Hardware
Chip M4 Pro (16c)
Memory 24 GB
GPU Cores 16
Software
oMLX v0.3.8
macOS macOS 15.6.1
Context 1,024