← Back to community benchmarks

Qwen3.5-9B

M3 Ultra (80c) · 512 GB · 8bit · 2026-03-13

Performance

64k

tokens

1,103

PP tok/s

38.8

TG tok/s

59439

TTFT (ms)

14.8

Peak mem (GB)

Hardware

Chip M3 Ultra (80c)

Memory 512 GB

GPU Cores 80

Software

oMLX v0.2.10

macOS macOS 15.3

Context 65,536

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
32k	1,294	47.9	12.7 GB	view
64k	1,103	38.8	14.8 GB	current