← Back to community benchmarks

Qwen3-30B-A3B-Instruct-2507

M3 Ultra (60c) · 256 GB · 8bit · 2026-03-09

Performance

4k

tokens

1,685

PP tok/s

63.8

TG tok/s

2431

TTFT (ms)

31.3

Peak mem (GB)

Hardware

Chip M3 Ultra (60c)

Memory 256 GB

GPU Cores 60

Software

oMLX v0.2.6

macOS macOS 15.6.1

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,410	74.4	30.8 GB	view
4k	1,685	63.8	31.3 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	74.4	1.00×
2×	125.4	1.69×
4×	181.0	2.43×