← Back to community benchmarks

Qwen2.5-0.5B-Instruct

M3 Pro (18c) · 36 GB · 4bit · 2026-03-11

Performance

1k

tokens

3,106

PP tok/s

251.0

TG tok/s

330

TTFT (ms)

0.8

Peak mem (GB)

Hardware

Chip M3 Pro (18c)

Memory 36 GB

GPU Cores 18

Software

oMLX v0.2.7

macOS macOS 26.3.1

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	3,106	251.0	0.8 GB	current
4k	4,303	204.8	1.1 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	251.0	1.00×
2×	434.6	1.73×
4×	540.9	2.15×