← Back to community benchmarks

Qwen3.6-35B-A3B-oQ4

M5 Max (40c) · 128 GB · 4bit · 2026-04-17

Performance

128k

tokens

1,254

PP tok/s

18.2

TG tok/s

104560

TTFT (ms)

31.1

Peak mem (GB)

Hardware

Chip M5 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.3.6

macOS macOS 26.5

Context 131,072

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,737	120.5	19.9 GB	view
4k	3,430	115.8	20.7 GB	view
8k	3,905	108.9	21.1 GB	view
16k	3,773	100.3	21.7 GB	view
32k	3,210	87.9	23.0 GB	view
64k	2,231	63.4	25.7 GB	view
128k	1,254	18.2	31.1 GB	current