← Back to community benchmarks

Qwen3.6-35B-A3B

M3 Ultra (60c) · 256 GB · 8bit · 2026-04-20

Performance

32k

tokens

1,734

PP tok/s

59.0

TG tok/s

18896

TTFT (ms)

38.5

Peak mem (GB)

Hardware

Chip M3 Ultra (60c)

Memory 256 GB

GPU Cores 60

Software

oMLX v0.3.6

macOS macOS 26.4.1

Context 32,768

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,763	224.2	36.7 GB	view
4k	921.9	82.6	36.2 GB	view
8k	2,117	78.6	36.5 GB	view
16k	2,001	72.0	37.1 GB	view
32k	1,734	59.0	38.5 GB	current
64k	1,313	48.9	41.2 GB	view