← Back to community benchmarks

Qwen3.5-35B-A3B-Heretic

M4 Pro (16c) · 48 GB · 4bit · 2026-03-10

Performance

4k

tokens

730.6

PP tok/s

77.6

TG tok/s

5607

TTFT (ms)

19.6

Peak mem (GB)

Hardware

Chip M4 Pro (16c)

Memory 48 GB

GPU Cores 16

Software

oMLX v0.2.6

macOS macOS 26.3.1

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
4k	730.6	77.6	19.6 GB	current
16k	650.9	61.4	20.2 GB	view
64k	426.6	32.6	22.7 GB	view