← Back to community benchmarks

Qwen3.5-35B-A3B

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

Performance

32k

tokens

1,177

PP tok/s

72.6

TG tok/s

27842

TTFT (ms)

22.3

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 32,768

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
4k	1,466	95.6	20.0 GB	view
16k	1,354	81.5	21.0 GB	view
32k	1,177	72.6	22.3 GB	current