← Back to community benchmarks

Qwen3.5-9B

M5 Pro (20c) · 64 GB · 4bit · 2026-03-21

Performance

4k

tokens

1,515

PP tok/s

55.0

TG tok/s

2703

TTFT (ms)

7.4

Peak mem (GB)

Hardware

Chip M5 Pro (20c)

Memory 64 GB

GPU Cores 20

Software

oMLX v0.2.19

macOS macOS 26.3.1

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,516	57.0	6.7 GB	view
4k	1,515	55.0	7.4 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	57.0	1.00×
2×	104.8	1.84×
4×	137.4	2.41×