← Back to community benchmarks

Qwen3.5-35B-A3B

M4 Pro (20c) · 64 GB · 4bit · 2026-03-10

Performance

32k

tokens

638.8

PP tok/s

56.2

TG tok/s

51296

TTFT (ms)

21.6

Peak mem (GB)

Hardware

Chip M4 Pro (20c)

Memory 64 GB

GPU Cores 20

Software

oMLX v0.2.6

macOS macOS 26.3.1

Context 32,768

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
32k	638.8	56.2	21.6 GB	current
64k	502.2	23.6	23.3 GB	view