← Back to community benchmarks

Qwen3.6-35B-A3B-UD

M4 Pro (20c) · 48 GB · 4bit · 2026-04-18

Performance

16k

tokens

822.3

PP tok/s

53.6

TG tok/s

19925

TTFT (ms)

21.9

Peak mem (GB)

Hardware

Chip M4 Pro (20c)

Memory 48 GB

GPU Cores 20

Software

oMLX v0.3.6

macOS macOS 26.3

Context 16,384

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
8k	882.4	60.3	21.3 GB	view
16k	822.3	53.6	21.9 GB	current
32k	700.6	44.4	23.3 GB	view