← Back to community benchmarks

Qwen3.6-35B-A3B-UD

M1 Max (32c) · 64 GB · 4bit · 2026-04-28

Performance

32k

tokens

524.9

PP tok/s

35.6

TG tok/s

62426

TTFT (ms)

23.5

Peak mem (GB)

Hardware

Chip M1 Max (32c)

Memory 64 GB

GPU Cores 32

Software

oMLX v0.3.6

macOS macOS 26.3.1

Context 32,768

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	411.2	132.0	21.7 GB	view
4k	385.6	53.8	21.2 GB	view
8k	595.9	49.4	21.5 GB	view
16k	576.3	43.9	22.2 GB	view
32k	524.9	35.6	23.5 GB	current
64k	418.8	25.4	26.2 GB	view