← Back to community benchmarks

Qwen3.5-4B

M1 Max (24c) · 32 GB · unknown · 2026-04-23

Performance

1k

tokens

418.8

PP tok/s

28.3

TG tok/s

2445

TTFT (ms)

8.8

Peak mem (GB)

Hardware

Chip M1 Max (24c)

Memory 32 GB

GPU Cores 24

Software

oMLX v0.3.7

macOS macOS 26.4.1

Context 1,024