← Back to community benchmarks

Qwen3.5-27B

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

Performance

1k

tokens

67.1

PP tok/s

15.5

TG tok/s

15265

TTFT (ms)

15.8

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