← Back to community benchmarks

Qwen3-Coder-30B-A3B-Instruct

M5 Pro (20c) · 64 GB · 4bit · 2026-07-04

Performance

32k

tokens

964.5

PP tok/s

40.1

TG tok/s

33973

TTFT (ms)

19.6

Peak mem (GB)

Hardware

Chip M5 Pro (20c)

Memory 64 GB

GPU Cores 20

Software

oMLX v0.4.4

macOS macOS 26.5.2

Context 32,768

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,207	98.1	16.6 GB	view
8k	1,733	56.6	17.5 GB	view
32k	964.5	40.1	19.6 GB	current