I run a local LLM on my gaming computer thats like a decade old now with an old 1070ti 8GB VRAM card. It does a good job running mistral small 22B at 3t/s which I think is pretty good. But any tech enthusiast into LLMs look at those numbers and probably wonder how I can stand such a slow token speed. I look at their multi card data center racks with 5x 4090s and wonder how the hell they can afford it.
Is something like jmp.chat sort of close?
You can’t just show sackboy and littlebigplanet in the thumbnail. you gave me hope it would be an article about how mediamolicule is back and lbp4 being announced. I gave up consoles after the ps3 but if theres one exclusive that could rope me back in it would be that. Fuck Sony you had one good series that I would love to bond over with my kids and you let it die a slow horrible death. If you played your cards right you could have had a game series that rivaled minecraft itself for popularity amongst everyone.
You can self host a local chatgpt like ai known as a local large language model. Searx and Searxbg are great customizable meta search engines that you can customize to scrape whatever you want
If your lucky she might be into it leading to some really nerdy gamer BDSM