← Back to community benchmarks

Qwen3.5-9B-OptiQ

M5 Pro (20c) · 64 GB · 4bit · 2026-03-22

Performance

4k

tokens

1,519

PP tok/s

50.3

TG tok/s

2696

TTFT (ms)

7.6

Peak mem (GB)

Hardware

Chip M5 Pro (20c)

Memory 64 GB

GPU Cores 20

Software

oMLX v0.2.20.dev1

macOS macOS 26.3.1

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,233	51.8	6.8 GB	view
4k	1,519	50.3	7.6 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	51.8	1.00×
2×	94.0	1.81×
4×	129.2	2.49×