← Back to community benchmarks

Qwen3.6-35B-A3B-RotorQuant

M1 Max (24c) · 32 GB · 4bit · 2026-04-17

Performance

16k

tokens

438.4

PP tok/s

45.2

TG tok/s

37374

TTFT (ms)

21.0

Peak mem (GB)

Hardware

Chip M1 Max (24c)

Memory 32 GB

GPU Cores 24

Software

oMLX v0.3.6

macOS macOS 26.2

Context 16,384

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	328.1	108.7	20.6 GB	view
4k	238.9	57.9	20.0 GB	view
8k	456.2	53.4	20.4 GB	view
16k	438.4	45.2	21.0 GB	current