← Back to community benchmarks

Qwen3.6-27B-MXFP4-MTP

M4 Max (32c) · 36 GB · 4bit · 2026-05-18
Performance
1k
tokens
190.1
PP tok/s
29.3
TG tok/s
5388
TTFT (ms)
15.9
Peak mem (GB)
Hardware
Chip M4 Max (32c)
Memory 36 GB
GPU Cores 32
Software
oMLX v0.3.8
macOS macOS 15.3
Context 1,024