← Back to community benchmarks

Qwen3.5-9B-Uncensored-HauhauCS-Aggressive

M5 (10c) · 32 GB · 8bit · 2026-04-29

Performance

16k

tokens

577.0

PP tok/s

12.6

TG tok/s

28395

TTFT (ms)

12.1

Peak mem (GB)

Hardware

Chip M5 (10c)

Memory 32 GB

GPU Cores 10

Software

oMLX v0.3.6

macOS macOS 26.4.1

Context 16,384

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	566.3	14.2	10.3 GB	view
4k	629.7	13.9	10.9 GB	view
8k	625.8	13.4	11.3 GB	view
16k	577.0	12.6	12.1 GB	current
32k	485.8	12.0	13.6 GB	view
64k	273.0	8.0	16.7 GB	view
128k	187.5	5.9	23.1 GB	view