Hacker News new | ask | show | jobs
by pheeney 499 days ago
What models would you recommend for basic classification if you don't need a 24B parameter one?
3 comments

You might find this comparison chart helpful: https://www.airtrain.ai/blog/how-15-top-llms-perform-on-clas...

Note: from October; also I work at Airtrain

I’m using Llama-3 8B to classify html files. It’s surprisingly good, and I run it on an RTX 4060 Ti at 8-bit quantization. No complains so far.
There's no alternative to testing with your own data. The majority of our data is in French, and our benchmarks differ greatly from public benchmarks generally based on English documents.