← Back to community benchmarks

Qwen3.6-27B-PARO

M4 Max (40c) · 128 GB · 4bit · 2026-06-15
Performance
1k
tokens
236.8
PP tok/s
26.1
TG tok/s
4324
TTFT (ms)
15.5
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.4.4rc1
macOS macOS 26.5.1
Context 1,024