← Back to community benchmarks

Qwen3.6-35B-A3B-UD

M1 Max (32c) · 64 GB · 4bit · 2026-04-25

Performance

16k

tokens

488.1

PP tok/s

42.0

TG tok/s

33568

TTFT (ms)

22.2

Peak mem (GB)

Hardware

Chip M1 Max (32c)

Memory 64 GB

GPU Cores 32

Software

oMLX v0.3.7

macOS macOS 26.3

Context 16,384

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	482.7	84.3	21.1 GB	view
4k	366.7	53.3	21.2 GB	view
8k	531.2	49.3	21.5 GB	view
16k	488.1	42.0	22.2 GB	current
32k	426.3	34.1	23.5 GB	view