← Back to community benchmarks

Qwen3.6-35B-A3B

M3 Ultra (60c) · 256 GB · 6bit · 2026-06-07

Performance

16k

tokens

1,889

PP tok/s

70.8

TG tok/s

8672

TTFT (ms)

29.1

Peak mem (GB)

Hardware

Chip M3 Ultra (60c)

Memory 256 GB

GPU Cores 60

Software

oMLX v0.4.2rc1

macOS macOS 26.5.1

Context 16,384

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,465	72.8	27.3 GB	view
4k	2,038	73.9	28.1 GB	view
8k	2,052	74.6	28.4 GB	view
16k	1,889	70.8	29.1 GB	current
32k	1,611	64.9	30.4 GB	view
64k	1,239	57.1	33.1 GB	view