← Back to community benchmarks

Qwen3.6-35B-A3B

M3 Ultra (60c) · 96 GB · 8bit · 2026-04-16

Performance

4k

tokens

2,053

PP tok/s

78.8

TG tok/s

1995

TTFT (ms)

36.2

Peak mem (GB)

Hardware

Chip M3 Ultra (60c)

Memory 96 GB

GPU Cores 60

Software

oMLX v0.3.5.dev1

macOS macOS 15.4.1

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
4k	2,053	78.8	36.2 GB	current
16k	1,970	68.4	37.1 GB	view
64k	1,283	29.5	41.2 GB	view