← Back to community benchmarks

Qwen3.5-35B-A3B

M4 Pro (16c) · 64 GB · 4bit · 2026-03-10

Performance

32k

tokens

575.1

PP tok/s

48.8

TG tok/s

56980

TTFT (ms)

21.6

Peak mem (GB)

Hardware

Chip M4 Pro (16c)

Memory 64 GB

GPU Cores 16

Software

oMLX v0.2.6

macOS macOS 26.3

Context 32,768

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
8k	717.7	74.5	20.4 GB	view
16k	665.6	63.1	20.8 GB	view
32k	575.1	48.8	21.6 GB	current
64k	448.1	30.6	23.3 GB	view