← Back to community benchmarks

Qwen3.6-35B-A3B-RotorQuant

M1 Pro (16c) · 32 GB · 3bit · 2026-04-24

Performance

16k

tokens

798.1

PP tok/s

17.7

TG tok/s

20530

TTFT (ms)

18.0

Peak mem (GB)

Hardware

Chip M1 Pro (16c)

Memory 32 GB

GPU Cores 16

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	236.2	76.4	16.6 GB	view
4k	173.1	45.1	16.6 GB	view
16k	798.1	17.7	18.0 GB	current