
LongCat 2.0: Open Mixture-of-Experts Model with 1.6T Parameters
Hacker News·1w·benjiro29
benjiro29 released LongCat 2.0, a large open-source language model using a mixture-of-experts architecture with 1.6 trillion total parameters but only 48 billion active during inference. For indie builders, this means cheaper inference costs than dense models of similar capability, with the full model weight available for self-hosting and fine-tuning.
Original story
Read the original on Hacker NewsRelated stories
AI
HYVE Ether OS goes on pre-sale: a $499 sovereign AI operating system you actually ownVibe Software Solutions·0mo·Anthony S. Owens

Open source
Geochemistry challenge to origin-of-life assumptions draws scrutinyHacker News·1mo·speckx

AI
Stanford releases open-source course on building language models from first principlesHacker News·1mo·kristianpaul