← Back to community benchmarks

Qwen3.5-35B-A3BMXFP4

M2 Max (30c) · 64 GB · 4bit · 2026-04-15

Performance

16k

tokens

638.0

PP tok/s

56.5

TG tok/s

25680

TTFT (ms)

22.8

Peak mem (GB)

Hardware

Chip M2 Max (30c)

Memory 64 GB

GPU Cores 30

Software

oMLX v0.3.5

macOS macOS 26.4.1

Context 16,384

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	602.2	163.2	21.2 GB	view
4k	550.1	77.6	20.8 GB	view
8k	696.0	69.7	21.5 GB	view
16k	638.0	56.5	22.8 GB	current
32k	534.2	37.5	25.4 GB	view