Entelligence AI

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.

1-bit Hy3 running locally is 2.2x faster than its API at the same quality! We gave both models the same task and compared one-shot outputs. 1-bit Hy3 295B GGUF (92GB) ran locally on 4x RTX 5090 with 128GB VRAM against the same Hy3 over cloud API Tasks: - Flappy Bird - Arkanoid - Snake Outputs: Hy3 1-bit local: 76.9K tokens, 15.5 min Hy3 cloud API: 75.1K tokens, 34.3 min The 1-bit games look the same as the API ones. Birds fly through the pipes, bricks break, the snake eats and grows. Nothing froze or crashed. Both models even made the same slip: the snake can cross itself and the game does not end. Getting this quality from 1 bit running locally is wild! Run Hy3 GGUF yourself in Atomic Chat in 2 clicks

Tomorrow might be 8M active user celebration day. Just saying

The next wave isn’t about writing better code. It’s about giving engineering leaders the intelligence to ship it. Who’s optimizing AI spend? Who’s measuring outcomes? Who’s making sure AI-generated code actually reaches production? These are the questions we’ve been building to answer. Over the next few weeks, we’ll be launching Model Router, Agent Insights, CLI, and more to help engineering teams optimize AI spend, measure what their agents actually deliver, and ship with confidence. New launches. Every week. Stay tuned.

The AI race isn't slowing down, it's changing At the beginning of 2026 everyone was obsessed with bigger models, longer context windows, and generating more code. Today the biggest challenge is keeping AI spend flat as usage keeps exploding Brian Armstrong recently highlighted routing as one of the biggest levers behind this shift That's exactly why we built Entelligence Model Router, same output, smarter routing, lower AI spend