← Back to community benchmarks

majentik--Qwen3.6-35B-A3B-TurboQuant

M4 Pro (16c) · 24 GB · 3bit · 2026-07-24

Performance

16k

tokens

683.8

PP tok/s

71.1

TG tok/s

23959

TTFT (ms)

16.6

Peak mem (GB)

Hardware

Chip M4 Pro (16c)

Memory 24 GB

GPU Cores 16

Software

oMLX v0.5.3

macOS macOS 26.5.2

Context 16,384

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
4k	785.8	82.6	16.0 GB	view
16k	683.8	71.1	16.6 GB	current
64k	455.2	46.2	18.3 GB	view