BEST SELLERS

In IPC / AI Systems

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 - Super quiet - Simple remote connection options - Preloaded Jupyterlab is convenient - Playbooks always getting added - NVIDIA ecosystem in a small package

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.

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

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