← Back to community benchmarks

Qwen3.6-35B-A3B

M4 Pro (16c) · 48 GB · 4bit · 2026-04-25

Performance

16k

tokens

678.2

PP tok/s

62.2

TG tok/s

24159

TTFT (ms)

21.0

Peak mem (GB)

Hardware

Chip M4 Pro (16c)

Memory 48 GB

GPU Cores 16

Software

oMLX v0.3.6

macOS macOS 15.7.2

Context 16,384

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	654.6	82.9	19.3 GB	view
4k	746.5	78.7	20.0 GB	view
8k	731.3	72.0	20.4 GB	view
16k	678.2	62.2	21.0 GB	current