PrismML launches Bonsai 27B, a model based on Qwen3.6 27B that it says runs natively on Apple devices via MLX; its CEO says Apple is evaluating the tech (MacKenzie Sigalos/CNBC)

Techmeme ·

PrismML released Bonsai 27B, a Qwen3.6-based model optimized to run locally on Apple hardware through MLX.

Categories: Model Releases

Excerpt

<a href="https://www.cnbc.com/2026/07/14/apple-prismml-ai-compression-iphone.html"><img align="RIGHT" border="0" hspace="4" src="http://www.techmeme.com/260714/i39.jpg" vspace="4" /></a> <p><a href="https://www.techmeme.com/260714/p39#a260714p39" title="Techmeme permalink"><img height="12" src="http://www.techmeme.com/img/pml.png" style="border: none; padding: 0; margin: 0;" width="11" /></a> MacKenzie Sigalos / <a href="http://www.cnbc.com/">CNBC</a>:<br /> <span style="font-size: 1.3em;"><b><a href="https://www.cnbc.com/2026/07/14/apple-prismml-ai-compression-iphone.html">PrismML launches Bonsai 27B, a model based on Qwen3.6 27B that it says runs natively on Apple devices via MLX; its CEO says Apple is evaluating the tech</a></b></span>&nbsp; &mdash;&nbsp; Apple is in talks with a small Silicon Valley company that says it can shrink powerful artificial intelligence models enough to run directly &hellip; </p>

Read at source: https://www.techmeme.com/260714/p39#a260714p39