Not true. 500Mb models suck ass and are just here for fun. A lot of local models in the 2.5Gb range can run on a phone and produce very coherent output on par with free-to-use LLMs without actually destroying the planet (while using them I mean, training is still a nightmare).
“Fun” fact, political bias is baked in the local models too, don’t ask Qwen3 about what happened in Tiananmen Square in 1989…
I haven’t been following much of the new developments of these self-hostable AI. Can you actually self-host anything decent?
I have played around these smaller models in the past and honestly anything smaller than LLama 4 Scout was just not very useful. Now Llama 4 Scout was “17B Active parameters, 16 experts and 109B Total parameters” so not sure what that even means.
local ai models you run on your own machine are better for your privacy, even if they’re nowhere as intelligent.
I’m pretty sure they’re exactly as “intelligent”: not at all
Technically correct but any suggestions on how to differentiate between the different qualities of models?
Local llms have barely reached the point where output is comprehensible, in the mean time chatgpt can effectively scam elderly people.
Not true. 500Mb models suck ass and are just here for fun. A lot of local models in the 2.5Gb range can run on a phone and produce very coherent output on par with free-to-use LLMs without actually destroying the planet (while using them I mean, training is still a nightmare).
“Fun” fact, political bias is baked in the local models too, don’t ask Qwen3 about what happened in Tiananmen Square in 1989…
I haven’t been following much of the new developments of these self-hostable AI. Can you actually self-host anything decent?
I have played around these smaller models in the past and honestly anything smaller than LLama 4 Scout was just not very useful. Now Llama 4 Scout was “17B Active parameters, 16 experts and 109B Total parameters” so not sure what that even means.