← Back to community benchmarks

Qwen3.6-35B-A3B

M3 Ultra (60c) · 96 GB · 4bit · 2026-04-24

Performance

16k

tokens

4,155

PP tok/s

52.2

TG tok/s

3943

TTFT (ms)

22.1

Peak mem (GB)

Hardware

Chip M3 Ultra (60c)

Memory 96 GB

GPU Cores 60

Software

oMLX v0.3.7rc2

macOS macOS 26.4.1

Context 16,384

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
8k	2,157	94.6	20.9 GB	view
16k	4,155	52.2	22.1 GB	current
32k	3,917	50.8	22.7 GB	view
64k	3,220	49.0	24.6 GB	view