← Back to community benchmarks

Qwen3-30B-A3B-Instruct-2507-4bit-ODWQ

M4 Pro (20c) · 48 GB · 4bit · 2026-03-14

Performance

16k

tokens

485.3

PP tok/s

40.5

TG tok/s

33759

TTFT (ms)

18.2

Peak mem (GB)

Hardware

Chip M4 Pro (20c)

Memory 48 GB

GPU Cores 20

Software

oMLX v0.2.11

macOS macOS 26.3.1

Context 16,384

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	759.9	76.8	16.6 GB	view
4k	730.7	64.9	17.1 GB	view
8k	632.2	52.8	17.4 GB	view
16k	485.3	40.5	18.2 GB	current