← Back to community benchmarks

Qwen3.5-35B-A3B

M4 Pro (20c) · 48 GB · 4bit · 2026-03-11

Performance

16k

tokens

765.3

PP tok/s

42.2

TG tok/s

21410

TTFT (ms)

20.8

Peak mem (GB)

Hardware

Chip M4 Pro (20c)

Memory 48 GB

GPU Cores 20

Software

oMLX v0.2.7

macOS macOS 15.7.3

Context 16,384

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
8k	864.4	59.2	20.4 GB	view
16k	765.3	42.2	20.8 GB	current
32k	673.0	21.6	21.6 GB	view
64k	502.2	15.0	23.3 GB	view