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

PrismML Releases Bonsai 27B: 1-bit and Ternary Builds of Qwen3.6-27B That Run on Laptops and Phones

5.9GB. That's all PrismML's Bonsai 27B needs to run on your laptop—quantized from Qwen's 27B model without capability loss.

Reporting by MarkTechPost 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

Quantization breakthroughs that democratize frontier-class model inference are reshaping deployment economics. Running 27B models on consumer hardware changes which orgs can afford real-time AI applications.

The key facts

7 to know

  1. Bonsai 27B is 1-bit and ternary quantization of Qwen3.6-27B

  2. Ternary variant: {−1, 0, +1} weights at 1.71 bits per weight

  3. Ternary model footprint: 5.9GB ideal size

  4. 1-bit variant uses binary {−1, +1} weights

  5. Both variants released under Apache 2.0

  6. Targets laptop and mobile deployment

  7. Architecture unchanged from source model

Go to the source

MarkTechPostmarktechpost.com

Publisher excerpt: PrismML just released Bonsai 27B. It is a low-bit representation of Qwen3.6-27B, not a new pretrain. The architecture is unchanged. Two variants ship under Apache 2.0. Ternary Bonsai 27B uses {−1, 0, +1} weights at a true 1.71 bits per weight. Its ideal size is 5.9GB. 1-bit Bonsai 27B uses binary…
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