← Back to community benchmarks

Qwen3.5-9B-MXF8

M5 (10c) · 24 GB · 8bit · 2026-04-28

Performance

1k

tokens

540.9

PP tok/s

100.4

TG tok/s

1893

TTFT (ms)

11.9

Peak mem (GB)

Hardware

Chip M5 (10c)

Memory 24 GB

GPU Cores 10

Software

oMLX v0.3.7

macOS macOS 26.4.1

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	540.9	100.4	11.9 GB	current
4k	403.2	14.9	10.6 GB	view
8k	732.6	14.6	10.9 GB	view