← Back to community benchmarks

Qwen3.6-35B-A3B-oQ8

M3 Ultra (80c) · 512 GB · 8bit · 2026-04-29

Performance

32k

tokens

902.4

PP tok/s

193.1

TG tok/s

36310

TTFT (ms)

39.8

Peak mem (GB)

Hardware

Chip M3 Ultra (80c)

Memory 512 GB

GPU Cores 80

Software

oMLX v0.3.8rc1

macOS macOS 26.4.1

Context 32,768

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	2,248	230.1	36.7 GB	view
8k	1,532	330.0	37.9 GB	view
32k	902.4	193.1	39.8 GB	current
128k	290.2	80.5	46.3 GB	view