← Back to community benchmarks

qwen3.6-35b-a3b

M3 Ultra (60c) · 96 GB · 4bit · 2026-04-29

Performance

16k

tokens

2,011

PP tok/s

75.8

TG tok/s

8147

TTFT (ms)

22.2

Peak mem (GB)

Hardware

Chip M3 Ultra (60c)

Memory 96 GB

GPU Cores 60

Software

oMLX v0.3.6

macOS macOS 26.4.1

Context 16,384

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,576	360.8	21.8 GB	view
4k	1,017	89.7	21.2 GB	view
8k	2,126	82.6	21.6 GB	view
16k	2,011	75.8	22.2 GB	current
32k	1,741	49.0	23.5 GB	view