k
keynews.ai
keynews.ai
FrontierThe story, in brief

Bonsai 27B is a full open reasoning model that fits on an iPhone

27B parameters. Under 4GB. Running on iPhone. PrismML just compressed away the on-device AI gap.

Reporting by The Decoder 1 min brief
Illustration of a transparent lens revealing connected networks across layers of paper.
Exploring the next frontier of AI research.AI illustration by KeyNews
The KeyNews take

Why it matters

Model compression is becoming a competitive capability battleground. PrismML's Bonsai 27B demonstrates that reasoning-class models can run locally with minimal performance loss, forcing a reckoning on where inference happens—and who controls the hardware-to-model fit.

The key facts

6 to know

  1. Bonsai 27B compressed to under 4GB from 27B parameters

  2. Maintains 90% of original performance in compression

  3. Math and coding benchmarks barely affected by compression

  4. Apple reportedly testing the technology

  5. Enables full reasoning models to run natively on iPhone

  6. Compression approach could shift competitive dynamics in on-device AI

Go to the source

The Decoderthe-decoder.com

Publisher excerpt: PrismML has compressed a 27-billion-parameter AI model to under 4 GB, small enough to run on an iPhone. In the company's own benchmarks, the smallest version keeps 90 percent of the original performance, with math and coding scores barely affected. Apple is reportedly already testing the…
Read original report
Back to today's editionMore frontier news

The wider picture

View all
Illustration of a transparent lens revealing connected networks across layers of paper.
AI illustration by KeyNews
Frontier01

Alibaba Unveils Zhenwu V900 — and Plans Qwen Models With Up to 10 Trillion Parameters

Alibaba is advancing on two fronts simultaneously: announcing a custom AI accelerator (Zhenwu V900) and committing to massive model scale (10T parameters for future Qwen releases). For practitioners, this matters as a credible third-party capability play outside the US-China licensing squeeze; for enthusiasts, it's a significant lab-race signal about training compute and parameter scaling as competitive levers.

TechRepublic
Illustration of a transparent lens revealing connected networks across layers of paper.
AI illustration by KeyNews
Frontier02

Kyutai Releases Voice of Reason: A Speech-Native Model that Solves Spoken Math with Reinforcement Learning

A new capability frontier: models that reason directly in speech without transcription bottlenecks. This changes how we think about multimodal reasoning and what's possible with open-weight releases at scale.

MarkTechPost
Illustration of a transparent lens revealing connected networks across layers of paper.
AI illustration by KeyNews
Frontier03

Claude Opus 5.5, GPT-6 Sol, GPT-6 Luna, and a new price war

Frontier labs are shipping upgraded reasoning and multimodal models in rapid succession, signaling acceleration in the capability race. Simultaneous price cuts reshape AI economics for practitioners.

Simon Willison