← Back to community benchmarks

Qwen3.6-27B-oQ4-mtp

M3 Max (30c) · 36 GB · 4bit · 2026-05-24
Performance
1k
tokens
157.7
PP tok/s
21.5
TG tok/s
6494
TTFT (ms)
16.7
Peak mem (GB)
Hardware
Chip M3 Max (30c)
Memory 36 GB
GPU Cores 30
Software
oMLX v0.3.10
macOS macOS 26.4
Context 1,024