Thank you gonna check it

Good idea for normal people that are not really knowing how and what to put on such a device

In theory this is great, but in reality this will be used very badly by big corporates and all of this shit world

Said *without docker

Basically wants to setup SearXNG without using docker but wants to understand how apache serves it

Would like to understand it to customize it a bit and serve the service to a port instead of an URL for example

Would like to make it “pseudo-public” thank you anyway

edited the original post sorry

Thx

One is based on Ubuntu, the other on Debian. I wouldn’t recommended and don’t like Ubuntu myself cause of their decisions in the FOSS world

Recommend you Linux mint.

But preferably use LMDE (Linux Mint Debian Edition) instead of Mint based on Ubuntu

Mistral --> pseudo-open-source

Linux --> not relates to Europe (but amazing choice)

Vivaldi --> only source available

Pls format your posts it’s so much easier to read

Pretty good project, but is it the future to have mainly web apps?

What is the link with rocm?

Thank you bing 😂😂

I’ve shared this AI because it’s one of the best fully open source AI

Instead of the traditional open models (like llama, qwen, gemma…) that are only open weight, this model says that it has :

Fully open-source release of model weights, training hyperparameters, datasets, and code

Making it different from other big tech “open” models. Tough it exists other “fully open” models like GPT neo, and more

Following this page it should be enough based on the requirements of qwen2.5-3B https://qwen-ai.com/requirements/

Dont know if this test in a good representation of the two AI, but in this case it seems pretty promising, the only thing missing is a high parameters model