← Back to community benchmarks

Qwen2.5-7B-Instruct-oQ4

M4 Pro (16c) · 24 GB · 4bit · 2026-04-06

Performance

1k

tokens

365.9

PP tok/s

50.9

TG tok/s

2799

TTFT (ms)

4.9

Peak mem (GB)

Hardware

Chip M4 Pro (16c)

Memory 24 GB

GPU Cores 16

Software

oMLX v0.3.2

macOS macOS 26.4

Context 1,024

Batching Results

Batch Size	TG tok/s	Speedup
1×	50.9	1.00×
2×	76.9	1.51×
4×	81.8	1.61×