Bonsai 2 27B: Near-Lossless Compression in a 9x Smaller Footprint(prismml.com)
551 points by JonSchneider | 176 comments
PrismML blog post announcing Bonsai 2 27B, a compressed language model claiming near-lossless quality at a 9x smaller footprint.
prismml.com on Hacker News
5 stories on the front page, newest first. Scroll down to watch the site change over time.
Bonsai 27B: A 27B-Class model that runs on a phone(prismml.com)
649 points by xenova | 230 comments
PrismML blog post announcing Bonsai 27B, a 27B-parameter-class language model designed to run locally on a phone.
1-Bit Bonsai Image 4B Image Generation for Local Devices(prismml.com)
438 points by modinfo | 186 comments
PrismML blog post announcing Bonsai Image 4B, a 1-bit and ternary quantized image generation model designed to run on local devices.
Show HN: 1-Bit Bonsai, the First Commercially Viable 1-Bit LLMs(prismml.com)
385 points by PrismML | 144 comments
Homepage of PrismML, a startup building ultra-dense, compact AI models such as its 1-bit Bonsai LLMs for smartphones and efficient datacenters.