Does the meta-llama/llama-3.3-70b-instruct:free model have a limit? It stopped working a few hours of use.
219 days ago(+1)
Thanks, doesn't seem to keep working so I'm trying to run it locally with LM Studio. I have a 7900 XTX and a Ryzen 9 7900X/64GB DDR5 RAM. Would you know the best settings to use to maximise performance? I saw someone on F95Zon that had 2,000,000 memory and 50K max token output. Does he have a super computer or is it an nVidia GPU thing?