← Back to community benchmarks

Qwen3.6-35B-A3B

M3 Ultra (60c) · 96 GB · 4bit · 2026-04-23

Performance

4k

tokens

2,047

PP tok/s

97.9

TG tok/s

2002

TTFT (ms)

20.0

Peak mem (GB)

Hardware

Chip M3 Ultra (60c)

Memory 96 GB

GPU Cores 60

Software

oMLX v0.3.8.dev1

macOS macOS 26.4.1

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
4k	2,047	97.9	20.0 GB	current
64k	1,286	45.9	25.0 GB	view
128k	837.6	27.3	30.4 GB	view