Mmastodon BusinessStartups first seen 16 h ago, last 15 h ago, peak #1
Samsung Labs releases sub-1-bit LLM compression method
Original: Sub-1-Bit LLM Compression via Latent Factorization Article URL: https:// github.com/SamsungLabs/LittleB it Comments URL:
Samsung Labs has published LittleBit, a new technique for compressing large language models below one bit per weight using latent factorization. The code is available on GitHub, and the release is drawing attention among AI researchers and developers interested in running large models on limited hardware with far lower memory requirements.
Why now: Interest in efficiently running large language models on consumer and edge hardware is driving discussion of a new extreme-compression method from Samsung Labs.
Rank over time, top of the chart is #1. 8 snapshots from 16 h ago to 15 h ago.
Evidence
API: https://socialmediatrends-api.osmike.com/v1/trends/1548761