← Back to community benchmarks

Qwen3.6-35B-A3B-UD

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

Performance

64k

tokens

324.2

PP tok/s

18.8

TG tok/s

202158

TTFT (ms)

26.2

Peak mem (GB)

Hardware

Chip M1 Max (24c)

Memory 64 GB

GPU Cores 24

Software

oMLX v0.3.6

macOS macOS 26.3

Context 65,536

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	view
32k	401.2	29.2	23.5 GB	view
64k	324.2	18.8	26.2 GB	current