← Back to community benchmarks

Qwen3.6-27B-MXFP4-MTP

M4 Max (32c) · 36 GB · 4bit · 2026-05-15
Performance
32k
tokens
167.4
PP tok/s
19.8
TG tok/s
195724
TTFT (ms)
20.1
Peak mem (GB)
Hardware
Chip M4 Max (32c)
Memory 36 GB
GPU Cores 32
Software
oMLX v0.3.8
macOS macOS 15.3
Context 32,768