← Back to community benchmarks

Qwen3.6-27B-w2g64

M4 Max (32c) · 36 GB · 2bit · 2026-05-02
Performance
1k
tokens
170.6
PP tok/s
12.8
TG tok/s
6003
TTFT (ms)
17.5
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