← Back to community benchmarks

Qwen3.6-35B-A3B-oQ6

M3 Max (40c) · 128 GB · 6bit · 2026-04-23

Performance

4k

tokens

273.3

PP tok/s

67.3

TG tok/s

14990

TTFT (ms)

47.9

Peak mem (GB)

Hardware

Chip M3 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.3.7

macOS macOS 26.4.1

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	875.6	187.5	47.9 GB	view
4k	273.3	67.3	47.9 GB	current
8k	1,353	58.7	48.3 GB	view
16k	1,976	30.8	49.4 GB	view
32k	2,307	29.9	50.0 GB	view
64k	1,902	29.3	52.0 GB	view