← Back to community benchmarks

Qwen3.6-35B-A3B-UD

M4 Pro (20c) · 48 GB · 4bit · 2026-05-04

Performance

1k

tokens

133.4

PP tok/s

36.8

TG tok/s

7676

TTFT (ms)

21.1

Peak mem (GB)

Hardware

Chip M4 Pro (20c)

Memory 48 GB

GPU Cores 20

Software

oMLX v0.3.8

macOS macOS 15.7.5

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	133.4	36.8	21.1 GB	current
4k	187.3	18.2	21.2 GB	view
8k	339.5	28.6	21.5 GB	view
16k	427.7	34.8	22.4 GB	view
32k	440.7	38.6	23.5 GB	view
64k	343.5	26.9	26.2 GB	view