← Back to community benchmarks

Qwen2.5-3B-Instruct

M4 (10c) · 16 GB · 6bit · 2026-03-10

Performance

4k

tokens

523.1

PP tok/s

33.7

TG tok/s

7831

TTFT (ms)

3.1

Peak mem (GB)

Hardware

Chip M4 (10c)

Memory 16 GB

GPU Cores 10

Software

oMLX v0.2.6

macOS macOS 26.0.1

Context 4,096