← Back to community benchmarks

Qwen3.5-35B-A3B

M3 Max (40c) · 48 GB · 4bit · 2026-05-04

Performance

16k

tokens

1,359

PP tok/s

82.1

TG tok/s

12059

TTFT (ms)

21.0

Peak mem (GB)

Hardware

Chip M3 Max (40c)

Memory 48 GB

GPU Cores 40

Software

oMLX v0.3.8

macOS macOS 26.3.1

Context 16,384

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
4k	1,453	94.8	20.0 GB	view
16k	1,359	82.1	21.0 GB	current
32k	1,164	72.6	22.7 GB	view