← Back to community benchmarks

Qwen3.5-9B-OptiQ

M4 (10c) · 16 GB · 4bit · 2026-06-05

Performance

1k

tokens

209.2

PP tok/s

15.8

TG tok/s

4895

TTFT (ms)

7.2

Peak mem (GB)

Hardware

Chip M4 (10c)

Memory 16 GB

GPU Cores 10

Software

oMLX v0.4.2.dev1

macOS macOS 26.5

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	209.2	15.8	7.2 GB	current
4k	215.8	15.5	7.7 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	15.8	1.00×
2×	32.0	2.03×
4×	36.1	2.28×