
Small footprint easy startup Cant beat the model size capability for the price currently.



Great design with better cooling than the standard. Linux build with custom NVIDIA kernel that supports OpenWebUI / Ollama for LLM inference. Runs ComfyUI well. Extremely customizable and works well for varied inference loads with much better / larger LLMs with its ~120GB available LPDDR5 VRAMthan would run on a standard RTX GPU w/ 16 - 32GB GDDR7 VRAM. I would buy another for the right price (less than $3500)

- Easy setup, it was ready to use immediately - Good cooling, and super quiet - Sturdy feel and design

This thing is truly amazing. Can run models up to 200 billion parameters. (Most of mine are between 70-120b, but my 24b "devstral" model is very useful for simple coding.) For a "personal AI" it's perfect. I use it to assist with sensitive client matters that I do not want to "share" with public AI services. Yes, it is brittle, but it is not hard to perform factory-restore using Nvidia's image - they have clear instructions posted and AI can help you if you need it. Be sure to use Nvidia's tool to create the boot thumb-drive. The unique hardware and driver situation makes this computer incompatible with other distros or OSes.













