Earlier quoted context omitted.
There's a lot of great work both around supporting memory efficient inference (like on a closer-to-consumer machine), as well as on open source code-focused models. A lot of people are excited about the Qwen3-Coder family of models: https://huggingface.co/collections/Qwen/qwen3-coder-687fc861... For running locally, there are tools like Ollama and LM Studio. Your hardware needs will fluctuate depending on what size/q…
Awesome. Great info, thanks Is this just a fun project for now, or could I actually benefit from it in terms of software production like I do with tools like claude code? I am interested in carefully tailoring it to specific projects, integrating curated personal notes, external documentation, scientific papers, etc via RAG (this part I've already written), and carefully chosing the tools available to the agent. If I…
https://www.youtube.com/watch?v=e-EG3B5Uj78&t=237s
"Run Deepseek R1 at Home on Hardware from $250 to $25,000: From Installation to Questions"
You can run Deepseek R1 with over 671B parameters at 4 T/s for ~$25,000 (USD). With AMD Ryzen™ Threadripper™ PRO 7995WX 96-Core, 192-Thread Processor and PNY NVIDIA RTX PRO 6000