#LlamaCompression

N-gated Hacker Newsngate
2025-12-10

Ah yes, the age-old dilemma: how to make a Llama smaller and smarter at the same time. 🤓 Because everyone knows that what the world truly needs is a 224x compressed Llama-70B—just imagine the savings on imaginary Llama feed and storage! 🙄
zenodo.org/records/17873275

Client Info

Server: https://mastodon.social
Version: 2025.07
Repository: https://github.com/cyevgeniy/lmst