← Back to community benchmarks

Qwen3.6-35B-A3B-UD

M1 Max (24c) · 64 GB · 4bit · 2026-04-26

Performance

16k

tokens

439.1

PP tok/s

38.5

TG tok/s

37316

TTFT (ms)

22.2

Peak mem (GB)

Hardware

Chip M1 Max (24c)

Memory 64 GB

GPU Cores 24

Software

oMLX v0.3.6

macOS macOS 26.3

Context 16,384

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	370.6	53.6	20.4 GB	view
4k	454.2	51.2	21.2 GB	view
8k	456.2	46.7	21.5 GB	view
16k	439.1	38.5	22.2 GB	current
32k	401.2	29.2	23.5 GB	view
64k	324.2	18.8	26.2 GB	view