← Back to community benchmarks

Qwen3.5-9B

M4 Pro (16c) · 24 GB · 4bit · 2026-03-09

Performance

1k

tokens

363.4

PP tok/s

49.4

TG tok/s

2818

TTFT (ms)

6.7

Peak mem (GB)

Hardware

Chip M4 Pro (16c)

Memory 24 GB

GPU Cores 16

Software

oMLX v0.2.6

macOS macOS 26.1

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	363.4	49.4	6.7 GB	current
4k	364.4	47.7	7.0 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	49.4	1.00×
2×	80.0	1.62×
4×	84.3	1.71×