News User runs an AI model on an Xbox 360 — 3-core PowerPC with 512 MB memory handles an AI model based on llama2.c

We need to see simple AI LLM on older GPUs, particularly VLIW4/TESLA/GMA X3000. If it'll run on that it'll run on anything in an individuals possession today. These proof of concepts are awesome but I think that should be the target as they are all 18-20 years old now. Every computer with integrated graphics can do what those listed above could do and much better.
 
This is another step towards EXO Lab’s goal of giving the average person access to AI, not limiting it to mega corporations that spend billions of dollars on top-of-the-line equipment and consume megawatts of power.

Is isn't a step towards anything. This is something someone did just to see if it could be done. A 60MB model running on a 360 is worthless to the average person. I'm sure the tokens per watt cost is far higher on the 360 than new hardware too.

There are plenty of free options to run an LLM on your own computer that aren't hard for the average person to understand or install.