← Back to community benchmarks

Qwen3.6-35B-A3B

M2 Pro (16c) · 32 GB · 4bit · 2026-04-24

Performance

4k

tokens

160.9

PP tok/s

54.7

TG tok/s

25460

TTFT (ms)

20.0

Peak mem (GB)

Hardware

Chip M2 Pro (16c)

Memory 32 GB

GPU Cores 16

Software

oMLX v0.3.7

macOS macOS 26.4.1

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	262.8	78.4	20.0 GB	view
4k	160.9	54.7	20.0 GB	current
8k	333.1	47.7	20.4 GB	view
16k	319.0	35.5	21.0 GB	view
32k	289.5	26.7	22.4 GB	view