← Back to community benchmarks

Qwen3.5-9B-OptiQ

M4 Pro (16c) · 24 GB · 4bit · 2026-06-05

Performance

4k

tokens

345.6

PP tok/s

32.0

TG tok/s

11852

TTFT (ms)

8.2

Peak mem (GB)

Hardware

Chip M4 Pro (16c)

Memory 24 GB

GPU Cores 16

Software

oMLX v0.4.2.dev2

macOS macOS 26.5

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	326.7	37.1	7.5 GB	view
4k	345.6	32.0	8.2 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	37.1	1.00×
2×	62.5	1.68×
4×	72.6	1.96×