← Back to community benchmarks

Qwen3-Coder-30B-A3B-Instruct

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

Performance

8k

tokens

2,038

PP tok/s

74.7

TG tok/s

4020

TTFT (ms)

17.5

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 8,192

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	266.6	90.1	22.0 GB	view
8k	2,038	74.7	17.5 GB	current
32k	1,119	40.2	19.6 GB	view