← Back to community benchmarks

Qwen3.6-35B-A3B

M5 Pro (16c) · 48 GB · 4bit · 2026-04-18

Performance

32k

tokens

1,558

PP tok/s

62.9

TG tok/s

21028

TTFT (ms)

22.4

Peak mem (GB)

Hardware

Chip M5 Pro (16c)

Memory 48 GB

GPU Cores 16

Software

oMLX v0.3.5

macOS macOS 26.4.1

Context 32,768

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
16k	1,801	78.3	21.0 GB	view
32k	1,558	62.9	22.4 GB	current
64k	1,118	30.3	25.0 GB	view