← Back to community benchmarks

Qwen3.6-35B-A3B

M1 Max (24c) · 64 GB · 4bit · 2026-05-04

Performance

16k

tokens

257.8

PP tok/s

65.1

TG tok/s

63549

TTFT (ms)

22.5

Peak mem (GB)

Hardware

Chip M1 Max (24c)

Memory 64 GB

GPU Cores 24

Software

oMLX v0.3.7

macOS macOS 26.4.1

Context 16,384

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	364.9	97.6	20.6 GB	view
4k	357.1	86.0	21.7 GB	view
8k	316.2	87.1	21.8 GB	view
16k	257.8	65.1	22.5 GB	current
32k	191.6	50.9	23.7 GB	view