← Back to community benchmarks

Qwen3-Coder-30B-A3B-Instruct

M3 Max (40c) · 64 GB · 4bit · 2026-07-24

Performance

32k

tokens

580.2

PP tok/s

42.0

TG tok/s

56475

TTFT (ms)

19.6

Peak mem (GB)

Hardware

Chip M3 Max (40c)

Memory 64 GB

GPU Cores 40

Software

oMLX v0.5.1

macOS macOS 26.5.2

Context 32,768

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
32k	580.2	42.0	19.6 GB	current
64k	343.8	25.0	25.8 GB	view