← Back to community benchmarks

Qwen3.5-9B

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

Performance

4k

tokens

1,579

PP tok/s

55.4

TG tok/s

2594

TTFT (ms)

7.4

Peak mem (GB)

Hardware

Chip M5 Pro (20c)

Memory 64 GB

GPU Cores 20

Software

oMLX v0.2.20.dev3

macOS macOS 26.3.1

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,600	57.0	6.7 GB	view
4k	1,579	55.4	7.4 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	57.0	1.00×
2×	104.9	1.84×
4×	140.2	2.46×