← Back to community benchmarks

qwen3.6-35b-a3b

M3 Ultra (60c) · 96 GB · 4bit · 2026-04-30

Performance

1k

tokens

1,808

PP tok/s

337.7

TG tok/s

567

TTFT (ms)

21.1

Peak mem (GB)

Hardware

Chip M3 Ultra (60c)

Memory 96 GB

GPU Cores 60

Software

oMLX v0.3.8

macOS macOS 26.4.1

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,808	337.7	21.1 GB	current
4k	778.1	89.7	21.7 GB	view
8k	2,122	84.3	22.1 GB	view