PrismML
PrismML is a startup focused on compressing large language models to run on consumer devices including smartphones and laptops. The company recently released Bonsai-27B, a quantized version of Qwen's 27-billion-parameter model compressed to 3.9-5.9GB using 1-bit and ternary weight compression techniques, and is in discussions with Apple about deploying larger models directly on iPhones to reduce latency and cloud costs while improving privacy.
Updated 3 August 2026
Signals
6 stories (new)
Media momentum
As of 3 Aug 2026 · Visible stories in the last 30 days, compared with the 30 days before.
4 sources
Source diversity
As of 3 Aug 2026 · Distinct publications behind this entity's visible coverage.
2 events
Release activity
As of 3 Aug 2026 · Model, product and open-source release events in the last 90 days whose coverage involves this entity.
—
Funding signals
As of 3 Aug 2026 · Funding and acquisition events in the last 90 days whose coverage involves this entity.
Jul 2026
Coverage span
As of 3 Aug 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 · 6 days ago ·
28
The Sequence Radar #897: Last Week in AI: China, Compression and the Open-Model Race
TheSequence · 2 weeks ago ·
36
Apple in talks with startup that shrinks AI models to run on an iPhone
TLDR · 2 weeks ago ·
19
[AINews] not much happened today
Latent Space · 2 weeks ago ·
19
PrismML Releases Bonsai 27B: 1-bit and Ternary Builds of Qwen3.6-27B That Run on Laptops and Phones
MarkTechPost · 2 weeks ago ·
14
Apple Exploring Ways to Run Much Larger AI Models Directly on iPhones
TLDR · 3 weeks ago ·
24
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 · 3 sources
- Develops llama.cpp · 1 source
- Derived from Qwen · 1 source
- Integrated with Qwen · 1 source
Partnerships
- Apple partnered with this company · 1 source