← Back to community benchmarks

Qwen3.6-27B-oQ6-mtp

M4 Max (32c) · 36 GB · 6bit · 2026-05-24
Performance
4k
tokens
176.2
PP tok/s
19.2
TG tok/s
23252
TTFT (ms)
24.4
Peak mem (GB)
Hardware
Chip M4 Max (32c)
Memory 36 GB
GPU Cores 32
Software
oMLX v0.3.9
macOS macOS 26.5
Context 4,096