← Back to community benchmarks

Qwen3.5-9B

M5 Pro (20c) · 64 GB · 4bit · 2026-03-18

Performance

1k

tokens

1,588

PP tok/s

57.0

TG tok/s

645

TTFT (ms)

6.7

Peak mem (GB)

Hardware

Chip M5 Pro (20c)

Memory 64 GB

GPU Cores 20

Software

oMLX v0.2.18

macOS macOS 26.3.1

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,588	57.0	6.7 GB	current
4k	1,646	55.3	7.4 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	57.0	1.00×
2×	104.4	1.83×
4×	138.3	2.43×