LinkTool
Running 27B-class models previously demanded high-end GPUs or cloud infrastructure. Extreme 1-bit and ternary quantisation brings complex agentic capabilities and multimodal reasoning directly to mobile devices and laptops, improving privacy and reducing infrastructure costs.
PrismML targets constraints in both edge hardware and datacentre power consumption through extreme model compression. By reducing precision down to 1-bit and ternary formats, Bonsai 27B fits inside 3.9 GB on an iPhone. If real-world benchmark performance matches the theoretical gains in intelligence density, this approach could shift autonomous agent execution directly onto end-user hardware.
Summary generated by AI (Gemini 3.8 Flash, 27 September 2026). It may contain errors – the original source is authoritative.
Similar in content, found by the AI search.
X post:Hamid Maei
PrismML has announced Ternary Bonsai 2 27B, a compressed version of Qwen3.8 27B. It is nine times smaller than the full-precision original, requiring only 5.9 GB of storage while retaining 98.2% of aggregate benchmark performance.
97bookmarks21kviews
X post:Udi Wertheimer
Udi Wertheimer highlights PrismML's release of Ternary Bonsai 2 27B, a model based on Qwen3.8 27B compressed to 5.9 GB while reportedly retaining 98.2% of its full-precision benchmark performance.
1.5kbookmarks260.1kviews
Article:trendforce.com
Caltech spinout PrismML has compressed Alibaba’s open-source Qwen 3.6 model from around 54 GB to under 4 GB to run directly on the iPhone 17 Pro. The breakthrough has reportedly led to meetings with Apple as it aims to expand on-device AI capabilities.
Article:Liquid AI
Liquid AI has launched LFM2.5-2.6B, an open-weight 2.6-billion parameter model engineered for local agentic workflows on phones, CPUs, and enterprise GPUs.
Link:inclusionAI
inclusionAI has introduced Ling-3.0-tiny, a compact MoE model with 7.9B total parameters activating only 1.3B parameters per token. Utilizing a hybrid architecture of linear and latent attention mechanisms, it aims to deliver efficient reasoning and agentic workloads on local hardware.
Article:Joe Rossignol
Apple has held discussions with startup PrismML to evaluate running substantially larger AI models directly on iPhones, according to a report by The Information. PrismML reportedly compressed Alibaba's 27-billion-parameter open-source model Qwen 3.6 to run entirely on an iPhone 17 Pro.
Parts of this content were created with the assistance of AI.
