← Back to community benchmarks

Qwen3.5-9B

M5 Pro (20c) · 48 GB · 8bit · 2026-04-26

Performance

1k

tokens

1,167

PP tok/s

32.4

TG tok/s

878

TTFT (ms)

9.9

Peak mem (GB)

Hardware

Chip M5 Pro (20c)

Memory 48 GB

GPU Cores 20

Software

oMLX v0.3.6

macOS macOS 26.4.1

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,167	32.4	9.9 GB	current
4k	1,479	31.9	10.6 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	32.4	1.00×
2×	60.4	1.86×
4×	90.9	2.81×