← Back to community benchmarks

Qwen3.6-35B-A3B-oQ6-mtp

M4 Pro (20c) · 48 GB · 6bit · 2026-07-24

Performance

16k

tokens

812.7

PP tok/s

54.7

TG tok/s

20159

TTFT (ms)

28.8

Peak mem (GB)

Hardware

Chip M4 Pro (20c)

Memory 48 GB

GPU Cores 20

Software

oMLX v0.5.3

macOS macOS 15.7.3

Context 16,384

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
16k	812.7	54.7	28.8 GB	current
32k	618.7	47.8	29.3 GB	view
64k	333.3	28.9	30.2 GB	view