← Back to community benchmarks

Qwen3.6-35B-A3B-Heretic

M4 Pro (16c) · 48 GB · 4bit · 2026-05-01

Performance

4k

tokens

190.9

PP tok/s

66.6

TG tok/s

21455

TTFT (ms)

20.0

Peak mem (GB)

Hardware

Chip M4 Pro (16c)

Memory 48 GB

GPU Cores 16

Software

oMLX v0.3.8

macOS macOS 26.4.1

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	500.9	154.9	20.6 GB	view
4k	190.9	66.6	20.0 GB	current
32k	503.0	46.8	22.4 GB	view