Unsloth runs Laya Decision models locally on just 4GB RAM across CPU, Mac and GPU

danielhanchen · x · 2026-09-28

UnslothAI announced that Laya Decision models can now run locally on devices with only 4GB of RAM, working across CPU, Mac, Windows, Linux and GPU setups. Models can be served through a compatible API via Unsloth Desktop. The repo (76.9k stars) is the first desktop app to both run and train local LLMs and diffusion models, supporting GGUF, MLX and many popular model families.

Original post →

More from Infra

Infra channel →