← Back to community benchmarks

Qwen3.5-9B

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

Performance

4k

tokens

1,543

PP tok/s

48.7

TG tok/s

2655

TTFT (ms)

7.4

Peak mem (GB)

Hardware

Chip M5 Pro (20c)

Memory 64 GB

GPU Cores 20

Software

oMLX v0.2.24

macOS macOS 26.4

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,591	50.1	6.7 GB	view
4k	1,543	48.7	7.4 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	50.1	1.00×
2×	93.1	1.86×
4×	129.0	2.57×