← Back to community benchmarks

Qwen3.6-35B-A3B-OptiQ

M5 Pro (16c) · 48 GB · 4bit · 2026-07-17

Performance

8k

tokens

2,058

PP tok/s

66.7

TG tok/s

3981

TTFT (ms)

22.9

Peak mem (GB)

Hardware

Chip M5 Pro (16c)

Memory 48 GB

GPU Cores 16

Software

oMLX v0.5.1

macOS macOS 26.5.2

Context 8,192

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,687	71.2	21.7 GB	view
4k	2,111	69.2	22.5 GB	view
8k	2,058	66.7	22.9 GB	current
16k	1,888	62.6	23.9 GB	view
32k	1,543	54.9	25.3 GB	view
64k	1,004	42.6	28.4 GB	view