Weekend project success! ✅ run Qwen3.5 35B on 3090 on old machine via llama.cpp ✅ use it from laptop on local network Not only it works but it is very capable and it gives me over 100 tokens / s ( 2000+ for prompt eval) It’s just… awesome. Thanks and for the inspiration from the podcast on sovereign AI. Next steps: use it securely from anywhere , find more old “cheap” hardware and set up more models, use them from Hermes agent … onward

Agreed

At least option B is true to its stated purpose. Prove you’re 18+. No other data is collected.

“Why does the company that profits from collecting user data draft legislation requiring every operating system to collect age data and broadcast it to every installed application via a system-level API? Why do these bills mandate commercial age verification vendors (Yoti, Veriff, Jumio) whose business model is collecting biometric data, while the EU's equivalent uses open-source zero-knowledge proofs that reveal nothing beyond "over 18"? “

I talk to my Vespa scooter though