← Back to community benchmarks

Qwen3.6-35B-A3B-oQ6

M5 Max (40c) · 128 GB · 6bit · 2026-04-30

Performance

128k

tokens

1,943

PP tok/s

43.1

TG tok/s

67469

TTFT (ms)

51.7

Peak mem (GB)

Hardware

Chip M5 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.3.8

macOS macOS 26.5

Context 131,072

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	2,997	352.5	29.4 GB	view
4k	2,877	335.6	30.5 GB	view
8k	1,921	93.5	29.5 GB	view
32k	4,762	46.3	33.4 GB	view
64k	3,269	45.3	39.5 GB	view
128k	1,943	43.1	51.7 GB	current