typeof

Engineer on Base 🔵 • Building BlockSocks 🧦 • Denver, CO 📍

Farcaster Development Boutique @ https://dTech.vision 💜 in love with tech 🤓decentralization, fitness and oldschool rap 😎

what are you doing with the model? so far I find it fun to play with but have no direct applied wow moment

I've got the DeepSeek-R1-Distill-Llama-70B-GGUF with Q4_K_M quantization loaded right now. It's generating ~10 tokens/sec. RAM usage is at 57%

what's the biggest r1 that comfortably works? R1 70b crashes Zed on my 64GB

serial founder § software engineer § privacy wonk § music head § theoretical memeticist

*slaps top of macbook*

This bad boy can fit so many parameters

Perfect to run that one LLM in full as your whole system. 😎