# PrismML Releases Bonsai 27B: First 27B Model to Run on Phones

> PrismML has released Bonsai 27B, a 27-billion-parameter multimodal model built to run entirely on a phone. According to the company, the smallest build weighs just 3.9GB and pushes around 11 tokens per second on an iPhone 17 Pro, while a ternary variant lands near 5.9GB. It shipped July 14 under a permissive Apache 2.0 license. The headline trick is aggressive quantization. By squeezing weights down to roughly one bit, PrismML claims the model holds onto 90 to 95 percent of its full-precision performance across text, images, reasoning, coding, and agentic tasks, which is the part worth checking as independent tests roll in. If the numbers hold, this is a meaningful step for on-device AI. A capable multimodal model that never has to phone home means lower latency, offline use, and a real privacy story, and it chips away at the assumption that serious models must live in someone else's data center.

_Section: [Daily AI Updates](https://www.wortins.com/daily-ai) · Source: PrismML · Published Tuesday, July 21, 2026_

## Wortins' read

PrismML has released Bonsai 27B, a 27-billion-parameter multimodal model built to run entirely on a phone. According to the company, the smallest build weighs just 3.9GB and pushes around 11 tokens per second on an iPhone 17 Pro, while a ternary variant lands near 5.9GB. It shipped July 14 under a permissive Apache 2.0 license. The headline trick is aggressive quantization. By squeezing weights down to roughly one bit, PrismML claims the model holds onto 90 to 95 percent of its full-precision performance across text, images, reasoning, coding, and agentic tasks, which is the part worth checking as independent tests roll in. If the numbers hold, this is a meaningful step for on-device AI. A capable multimodal model that never has to phone home means lower latency, offline use, and a real privacy story, and it chips away at the assumption that serious models must live in someone else's data center.

## Source

[Read the full story at PrismML](https://prismml.com/news/prismml-releases-bonsai-27b)

## Related coverage

- [A look at why the oft-discussed predictions that AI will deliver double-digit GDP growth in advanced economies are extremely unlikely over the next 10-15 years (Ghosts of Electricity)](https://www.wortins.com/story/a-look-at-why-the-oft-discussed-predictions-that-ai-will-del-6241fa38) — [Techmeme](https://www.techmeme.com/260910/p10#a260910p10)
- [IBM and NASA release an open-source lunar foundation model](https://www.wortins.com/story/ibm-and-nasa-release-an-open-source-lunar-foundation-model-0522b9e8) — [The Next Web](https://thenextweb.com/news/nasa-ibm-lunar-foundation-model-open-source)
- [OpenAI launches ChatGPT Images 2.5 with faster editing](https://www.wortins.com/story/openai-launches-chatgpt-images-2-5-with-faster-editing-07e86379) — [TestingCatalog](https://www.testingcatalog.com/openai-launches-chatgpt-images-2-5-with-faster-editing/)
- [Microsoft has new AI privacy rules for schools](https://www.wortins.com/story/microsoft-has-new-ai-privacy-rules-for-schools-6e0b8ab0) — [The Verge](https://www.theverge.com/policy/992359/microsoft-aft-schools-ai-privacy)
- [Clearview AI Is Testing an AI Tool That Would Let Cops Unearth Your Life Online](https://www.wortins.com/story/clearview-ai-is-testing-an-ai-tool-that-would-let-cops-unear-8c573d0e) — [Wired](https://www.wired.com/story/clearview-ai-is-testing-an-ai-tool-that-lets-cops-instantly-unearth-your-online-activity/)
- [Top AI spenders cut per-employee costs by nearly 10 percent in August](https://www.wortins.com/story/top-ai-spenders-cut-per-employee-costs-by-nearly-10-percent--b31ffb0b) — [The Decoder](https://the-decoder.com/top-ai-spenders-cut-per-employee-costs-by-nearly-10-percent-in-august/)

---

_Curated and written by [Wortins](https://www.wortins.com) — The daily AI briefing. Every story links to its original source; the "Wortins read" on each is our own original analysis. [About Wortins & our editorial approach](https://www.wortins.com/about)._