← Back to community benchmarks

Qwen3.5-9B-OptiQ

M4 (10c) · 16 GB · 4bit · 2026-03-11

Performance

4k

tokens

223.1

PP tok/s

19.1

TG tok/s

18358

TTFT (ms)

6.9

Peak mem (GB)

Hardware

Chip M4 (10c)

Memory 16 GB

GPU Cores 10

Software

oMLX v0.2.8b1

macOS macOS 26.2

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	216.0	19.6	6.6 GB	view
4k	223.1	19.1	6.9 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	19.6	1.00×
2×	39.0	1.99×
4×	51.1	2.61×