PrismML
Company prismml.com ● Covered in 7 stories + Follow ✴ AI Graph
PrismML is a company focused on compressing large AI models for local smartphone and laptop inference. In recent coverage, it released Bonsai 27B (based on Qwen3.6-27B), including 1-bit and ternary builds sized around 3.9GB and 5.9GB that are designed to run on-device, and it published deployment workflows using a llama.cpp fork with GPU support. PrismML has also been reported as being in talks with Apple after publicly optimizing a Qwen model to fit on iPhone devices, and its work has been described as part of a broader move toward edge deployment and compressed-model “lineage.”
Updated 11 September 2026
Signals
1 story (+0%)
Media momentum
As of 17 Sep 2026 · Visible stories in the last 30 days, compared with the 30 days before.
4 sources
Source diversity
As of 17 Sep 2026 · Distinct publications behind this entity's visible coverage.
2 events
Release activity
As of 17 Sep 2026 · Model, product and open-source release events in the last 90 days whose coverage involves this entity.
—
Funding signals
As of 17 Sep 2026 · Funding and acquisition events in the last 90 days whose coverage involves this entity.
Jul 2026 → Sep 2026
Coverage span
As of 17 Sep 2026 · First to most recent month of TLDRocket coverage of this entity.
Latest developments
Deploying a 1-Bit Bonsai-27B Model with PrismML llama.cpp and OpenAI-Compatible Local Inference Workflows
MarkTechPost · 1 month ago ·
33
The Sequence Radar #897: Last Week in AI: China, Compression and the Open-Model Race
Substack · 1 month ago ·
38
Apple in talks with startup that shrinks AI models to run on an iPhone
CNBC · 2 months ago ·
20
[AINews] not much happened today
Latent Space · 2 months ago ·
22
PrismML Releases Bonsai 27B: 1-bit and Ternary Builds of Qwen3.6-27B That Run on Laptops and Phones
MarkTechPost · 2 months ago ·
19
Apple Exploring Ways to Run Much Larger AI Models Directly on iPhones
MacRumors · 2 months ago ·
28
September 2026
July 2026
Moonshot AI releases Kimi K3, a 2.8 trillion parameter open-weight model achieving frontier-class performance Open source release
OpenAI's Codex reaches 8 million users following GPT-5.6 launch, experiencing rapid growth and scaling challenges Product launch
- Deploying a 1-Bit Bonsai-27B Model with PrismML llama.cpp and OpenAI-Compatible Local Inference Workflows
- The Sequence Radar #897: Last Week in AI: China, Compression and the Open-Model Race
- Apple in talks with startup that shrinks AI models to run on an iPhone
- [AINews] not much happened today
- PrismML Releases Bonsai 27B: 1-bit and Ternary Builds of Qwen3.6-27B That Run on Laptops and Phones
- Apple Exploring Ways to Run Much Larger AI Models Directly on iPhones
Relationships
Products & technology
- Develops Bonsai 27B · 4 sources
- Develops llama.cpp · 1 source
- Derived from Qwen · 1 source
- Integrated with Qwen · 1 source
Partnerships
- Apple partnered with this company · 1 source