
Daniel
604 posts

Daniel
@Daniel00Higgins
Salt life | Florida Fishing | Still have no idea what twitters for...


Today, we’re announcing Bonsai 27B: the first 27B-class model to run on a phone. Bonsai 27B is the new multimodal flagship of the Bonsai family. Based on Qwen3.6 27B, it brings a new capability tier to local AI: multi-step reasoning, structured tool use, long-context workflows, and coherent agentic loops. Until now, models in this class have been impractical to deploy locally. A 27B model occupies roughly 54 GB in 16-bit precision, and even a strong 4-bit build is around 18GB - too large for a phone and for most laptops. Bonsai 27B changes that. It comes in two variants: • Ternary Bonsai 27B: 5.9 GB, 1.71 effective bits per weight, optimized for laptop-class quality. • 1-bit Bonsai 27B: 3.9 GB, 1.125 effective bits per weight, optimized for phone-class footprint. Everything is open-sourced today under the Apache 2.0 license.









The Dilemna: 🤨 Do you buy a shiney new 2027 Model Y L for $61,990? OR a 2024 Model X (Refresh) for $59,995?




¿Qué lo que Miami? Robotaxi now available in Miami



Introducing Agents-A1, A 35B MoE agentic model built for long-horizon tasks across search, engineering, scientific research, instruction following, and tool calling. 🤖 modelscope.ai/models/InternS… 📚 256K context length + 🧠 Agentic reasoning 🏆 Reaches SOTA results on long-horizon search, scientific research, and instruction-following benchmarks, with competitive results among 35B-class models. 🛠️Supports function calling and tool integration, enabling interaction with APIs, code interpreters, search engines, and other external tools.




@googlegemma Yeah, adorable ;) Single 3090, cyankiwi/gemma-4-26B-A4B-it-qat-AWQ-INT4



The key to precision in manufacturing small, complex parts is the Matsuura MX-330. With a full 5-axis, setups are condensed for better accuracy, staying rigid and precise. This is American manufacturing. 🇺🇲




@elonmusk @DrEliDavid .@elonmusk! Headline not accurate. $6B will not solve world hunger, but it WILL prevent geopolitical instability, mass migration and save 42 million people on the brink of starvation. An unprecedented crisis and a perfect storm due to Covid/conflict/climate crises.

Elon Musk dismantled USAID programs that provided lifesaving assistance to millions of the world’s poorest and most vulnerable people. The human cost was enormous, while DOGE’s net fiscal impact was inconsequential. Now, as Musk approaches trillionaire status, he should commit/tithe at least $100 billion to a fund dedicated to combating extreme poverty, hunger, preventable disease, and humanitarian crises worldwide. Money alone cannot undo the damage already done. But if this moment marks an unprecedented personal financial milestone, it should also be an opportunity for an unprecedented act of restitution. Musk has the resources to save and improve countless lives. He should use them.












