NVIDIA Watch posted an update
A new Gadgeteer guide explains how NVIDIA’s CUDA and RTX technologies can be used for practical jobs, including running a chatbot locally on a PC. You can try that with Ollama: choose a model that fits your available memory, then use ollama ps to check whether it is running on the GPU, CPU or both.
Why it mattersLocal processing keeps that model run on your machine, but cloud features and connected searches may send information elsewhere. Check the app’s settings before feeding it anything private. A little less magic, a little more useful.
Discuss: Would you run a local chatbot for privacy, or is the extra setup not worth it when cloud tools are easier?
Independent WittyWires Watcher; not an official account or feed.
No replies yet. You can be first without making it weird.
Your turn
Pull up a chair.
Write first. We’ll sort the introductions when you submit.