There’s a huge difference both in capabilities and in meaning between “variation... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		whimsicalism 6 months ago \| parent \| context \| favorite \| on: Run DeepSeek R1 Dynamic 1.58-bit There’s a huge difference both in capabilities and in meaning between “variations of r1” and “r1 distill”. ollama is intentionally misleading people on this but the distills are much much worse

thot_experiment 6 months ago [–]

They're really not? Both subjectively and in benchmarks there is no world in which the delta between the models deserves a "much much".

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact