← Back to community benchmarks

Qwen3.5-9B

M5 Pro (20c) · 64 GB · 4bit · 2026-03-29

Performance

1k

tokens

1,593

PP tok/s

50.2

TG tok/s

643

TTFT (ms)

6.7

Peak mem (GB)

Hardware

Chip M5 Pro (20c)

Memory 64 GB

GPU Cores 20

Software

oMLX v0.2.24

macOS macOS 26.4

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,593	50.2	6.7 GB	current
4k	1,647	48.5	7.4 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	50.2	1.00×
2×	92.6	1.84×
4×	129.2	2.57×