← Back to community benchmarks

Qwen3.6-35B-A3B

M5 Pro (16c) · 48 GB · 4bit · 2026-07-23

Performance

4k

tokens

2,181

PP tok/s

93.1

TG tok/s

1878

TTFT (ms)

20.2

Peak mem (GB)

Hardware

Chip M5 Pro (16c)

Memory 48 GB

GPU Cores 16

Software

oMLX v0.5.3

macOS macOS 26.5.2

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
4k	2,181	93.1	20.2 GB	current
16k	1,941	82.4	21.2 GB	view
64k	1,214	56.0	25.5 GB	view