← Back to community benchmarks

Qwen3.6-27B

M4 Max (32c) · 36 GB · 4bit · 2026-04-26
Performance
8k
tokens
198.9
PP tok/s
20.4
TG tok/s
41180
TTFT (ms)
17.9
Peak mem (GB)
Hardware
Chip M4 Max (32c)
Memory 36 GB
GPU Cores 32
Software
oMLX v0.3.6
macOS macOS 26.4.1
Context 8,192