← Back to community benchmarks

Qwen3.6-27B-MXFP4-MTP

M5 Max (40c) · 64 GB · 4bit · 2026-05-13
Performance
1k
tokens
793.4
PP tok/s
45.2
TG tok/s
1291
TTFT (ms)
16.0
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 64 GB
GPU Cores 40
Software
oMLX v0.3.8
macOS macOS 26.4.1
Context 1,024