AI BriefingPrism ML releases Ternary Bonsai 2 models (2B, 4B, 9B) with browser-based WebGPU support
Key point
The 2B parameter model achieves up to 500 tokens per second locally in the browser on an M4 Max using custom WebGPU kernels.
Details
Prism ML has released Ternary Bonsai 2, a new family of small language models available in 2B, 4B, and 9B parameter sizes. The models are hosted on Hugging Face under the prism-ml collection.
A key highlight is the 2B model's ability to run entirely locally within a web browser. By utilizing custom WebGPU kernels, it achieves inference speeds of up to 500 tokens per second on an M4 Max chip. A WebGPU demo is also available via the webml-community Hugging Face space.
This summary was generated automatically by AI. Check the original for the author's claims and context. Copyright belongs to the original author.
Our guide explains how the AI works. Report summary errors, attribution issues, or removal requests via Contact.
Related
Microsoft introduces Microsoft-Decision-1, a low-latency model for structured decision-makingKrea 3 Launches: Frontier Image Editing Model Claims 10x Speed of Nano Banana Pro