March 12Mar 12 I am thinking of joining the Unraid ship! Apart from using it for storage I would love to run local AI models like gemma3:4b (3.3GB) or even qwen:14b (8.2GB) on it (and provide them to my local network).What hardware (motherboard & GPU or even a complete build) should I look for to get reasonable response times?(A t the moment I use gemma3 on my M2 Mac. For longer prompts it can take minutes to get a response. That is too long.)Many thanks for pointers!
Join the conversation
You can post now and register later. If you have an account, sign in now to post with your account.
Note: Your post will require moderator approval before it will be visible.