Bonsai 27B (1-bit LLM): The First 27B-Class Model to Run on a Phone
The Bonsai 27B model has been released as the first 27B-class AI model capable of running locally on a smartphone. By utilizing 1-bit and ternary weight quantization, the model achieves high-level reasoning and agentic capabilities within a small memory footprint.
Why it matters
This represents a major breakthrough in edge computing, enabling powerful AI capabilities to function offline on consumer mobile devices without relying on cloud servers.
Today, we're announcing Bonsai 27B, based on Qwen3.6 27B, the new multimodal flagship of the Bonsai family and the first model of its capability class to run on a phone.
Technical announcement focused on product capabilities and performance metrics.
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in