← Back to community benchmarks

models--leonsarmiento--Qwen3.6-27B-3bit

M1 Max (24c) · 32 GB · 4bit · 2026-06-05

Performance

1k

tokens

66.5

PP tok/s

14.1

TG tok/s

15401

TTFT (ms)

13.2

Peak mem (GB)

Hardware

Chip M1 Max (24c)

Memory 32 GB

GPU Cores 24

Software

oMLX v0.3.12

macOS macOS 26.4.1

Context 1,024