← Back to community benchmarks

Qwen3.6-35B-A3B

M3 Max (40c) · 64 GB · 8bit · 2026-05-05

Performance

1k

tokens

1,226

PP tok/s

257.1

TG tok/s

835

TTFT (ms)

36.1

Peak mem (GB)

Hardware

Chip M3 Max (40c)

Memory 64 GB

GPU Cores 40

Software

oMLX v0.3.8

macOS macOS 26.4.1

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,226	257.1	36.1 GB	current
4k	814.4	233.8	37.2 GB	view
8k	538.6	65.2	36.5 GB	view
16k	1,349	63.5	37.1 GB	view