← Back to community benchmarks

Qwen3.6-35B-A3B

M5 Max (40c) · 128 GB · unknown · 2026-04-18

Performance

16k

tokens

3,530

PP tok/s

64.0

TG tok/s

4642

TTFT (ms)

67.4

Peak mem (GB)

Hardware

Chip M5 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.3.6

macOS macOS 26.5

Context 16,384

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,865	71.1	65.6 GB	view
4k	3,357	69.2	66.4 GB	view
8k	3,627	67.4	66.7 GB	view
16k	3,530	64.0	67.4 GB	current
32k	3,112	56.9	68.7 GB	view
64k	2,367	45.8	71.3 GB	view
128k	1,519	33.4	76.8 GB	view