← Back to community benchmarks

Qwen3.6-35B-A3B

M1 Max (32c) · 64 GB · 6bit · 2026-04-26

Performance

16k

tokens

1,461

PP tok/s

26.5

TG tok/s

11213

TTFT (ms)

30.0

Peak mem (GB)

Hardware

Chip M1 Max (32c)

Memory 64 GB

GPU Cores 32

Software

oMLX v0.3.7

macOS macOS 26.4.1

Context 16,384

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	447.9	132.0	28.7 GB	view
4k	285.7	50.0	28.5 GB	view
8k	570.8	46.9	28.9 GB	view
16k	1,461	26.5	30.0 GB	current
32k	1,406	26.1	30.6 GB	view
64k	1,169	25.2	32.5 GB	view
128k	752.7	24.1	35.2 GB	view