I don't know what your - and your kid's - situation is, but I worry pushing Linux onto someone would be counterproductive to getting them to like it.
I only use it because I genuinely like and appreciate it. I'd probably start by getting him interested in it. If he likes it enough then he'll try and learn more by himself.
I recently got an LLM running locally on an AMD GPU. This was only possible on Linux. Depending on your son, something like that could be a cool way to get him interested.
Yeah, I also don't wanna push it too hard.
Gonna be hard though. He's way too into roblox these days.
Can you tell me something about what card you used to run what llm? What is its performance?
There is so little out there about this.
I have an RX6800XT and I use KoboldCPP to run models I download off of Huggingface.
I'm not sure how many tokens per second it generates, probably about 10?
I don't know what your - and your kid's - situation is, but I worry pushing Linux onto someone would be counterproductive to getting them to like it.
I only use it because I genuinely like and appreciate it. I'd probably start by getting him interested in it. If he likes it enough then he'll try and learn more by himself.
I recently got an LLM running locally on an AMD GPU. This was only possible on Linux. Depending on your son, something like that could be a cool way to get him interested.
Yeah, I also don't wanna push it too hard.
Gonna be hard though. He's way too into roblox these days.
Can you tell me something about what card you used to run what llm? What is its performance?
There is so little out there about this.
I have an RX6800XT and I use KoboldCPP to run models I download off of Huggingface.
I'm not sure how many tokens per second it generates, probably about 10?
If you want to try it yourself here's a link to the Github page: https://github.com/LostRuins/koboldcpp