← Back to community benchmarks

Qwen3-Coder-30B-A3B-Instruct

M3 Max (40c) · 128 GB · 4bit · 2026-03-14

Performance

4k

tokens

1,202

PP tok/s

70.5

TG tok/s

3407

TTFT (ms)

17.1

Peak mem (GB)

Hardware

Chip M3 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.2.8

macOS macOS 26.3.1

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,203	83.6	16.6 GB	view
4k	1,202	70.5	17.1 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	83.6	1.00×
2×	130.4	1.56×
4×	168.9	2.02×