← Back to community benchmarks

Qwen3.6-35B-A3B-oQ4

M4 Pro (16c) · 64 GB · 4bit · 2026-04-29

Performance

16k

tokens

1,440

PP tok/s

24.6

TG tok/s

11379

TTFT (ms)

22.6

Peak mem (GB)

Hardware

Chip M4 Pro (16c)

Memory 64 GB

GPU Cores 16

Software

oMLX v0.3.8rc1

macOS macOS 26.4

Context 16,384

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	527.0	152.0	20.6 GB	view
4k	185.6	67.4	21.1 GB	view
8k	656.4	63.6	21.4 GB	view
16k	1,440	24.6	22.6 GB	current
32k	1,387	23.9	23.2 GB	view
64k	1,118	22.5	25.1 GB	view