{"type":"rich","version":"1.0","title":"umbrel wrote","author_name":"umbrel (npub1ag…lmhct)","author_url":"https://nostr.now/npub1aghreq2dpz3h3799hrawev5gf5zc2kt4ch9ykhp9utt0jd3gdu2qtlmhct","provider_name":"njump","provider_url":"https://nostr.now","html":"Introducing LlamaGPT — a self-hosted, offline and private AI chatbot, powered by Llama 2, with absolutely no data leaving your device. 🔐\n\nYes, an entire LLM. ✨\n\nYour Umbrel Home, Raspberry Pi (8GB) Umbrel, or custom umbrelOS server can run it with just 5GB of RAM!\n\nWord generation benchmarks:\n\nUmbrel Home: ~3 words/sec\nRaspberry Pi (8GB RAM): ~1 word/sec\n\n→ Watch the demo: https://youtu.be/iu3_1a8SzeA \n\n→ Install on umbrelOS: https://apps.umbrel.com/app/llama-gpt\n\n→ GitHub: https://github.com/getumbrel/llama-gpt"}