Qwen3.8-27B Open Weights Coming, Runs Locally on 17GB RAM

danielhanchen · x · 2026-08-03

UnslothAI announced that Alibaba's Qwen3.8-27B model is coming soon. Optimized for accessibility, the model will run locally on setups with just 17GB of RAM/VRAM, significantly lowering the hardware barrier for deploying high-end LLMs locally.

Additionally, Alibaba previewed the open-weights release of its flagship 2.4T parameter model, Qwen3.8-Max, next week, which demonstrates exceptional capabilities in autonomous coding and long-horizon planning.

Original post →

More from Infra

Infra channel →