# @FoldingNapkins — 2026-09-11

♥0 ↻0 · https://x.com/FoldingNapkins/status/2098341815678050326

@vineerpasam Vibe code with local models then if you're afraid of corporate espionage. 

Qwen3.8:27b and gpt-oss:20b are both good models you can fit in under 16GB of RAM.

Some benchmarks I ran recently, summarised: https://t.co/r80CuXPbkT

tags: author:foldingnapkins, kind:tweet, on:qwen-3-8-27b, year:2026
cited on: _dossiers/qwen-3-8-27b.md, qwen-3-8-27b