Hacker News Reader

Not to mention that almost every model release has some (at least) minor issue in the prompt template and/or the runtime itself, so even if they (not talking unsloth specifically, in general) claim "Day 0 support", do pay extra attention to actual quality as it takes a week or two before issues been hammered out.

View on HN

Yes this is fair - we try our best to communicate issues - I think we're mostly the only ones doing the communication that model A or B has been fixed etc.

We try our best as model distributors to fix them on day 0 or 1, but 95% of issues aren't our issues - as you mentioned it's the chat template or runtime etc

I have to ask - what do you run locally on your laptop (model, backend, and agentic cli)?

Feature request:

A leader board with filtering so you can enter your machine specs and it will sort all models along with all the various quantisation and then rank them all - because so far model ranking site either don’t include all available quants, don’t compare apples to apples (ie was one model tested with Claude code while another benchmark done with opencode) etc

Oh - and as bonus, scoring also ranked by which agentic CLI :)

Reply on news.ycombinator.com