Holo4: powering generalist computer-use agents

Hugging Face Blog · Publicado el 28 sept 2026

Holo4 is a series of agentic models comprising a 27B dense model and a 35B-A3B Mixture of Experts model, both accessible via the H Models API, alongside an updated Holotron4 Nano. It interacts with software through GUIs, code, MCP, and APIs, selecting the most suitable interface per task rather than being constrained to one. Its training data comes from an internal Agentic Task Factory that generates approximately 10,000 verifiable tasks from documentation—including screenshots and open-source software—across web apps, MCP servers, desktop environments, and hybrid GUI/MCP setups. Lee 3 puntos de vista con sus evidencias y enlaces a las fuentes.

Maxime Theillard, Frederic Renard, Vincent Coyette, Emrick Sinitambirivoutin, Avshalom Manevich, Antonio Loison, Antoine Bonnet, Maxime Langevin, Aleix Cambray (H-AI), Léonard Benedetti, Tony Wu, Mats L. Richter, Michael Eickenberg, Sławek Mucha, Matthias Brunel, Daniel Beechey

Leer los puntos clave Abrir Editor

De un vistazo

Two-size agentic model series
Holo4 is released in two sizes: a 27B dense model and a 35B-A3B Mixture of Experts model, both available via the H Models API, alongside an updated Holotron4 Nano.
Ver el momento de apoyo · Párrafo 1
Unified model for GUI, code, MCP, and API interfaces
Holo4 interacts with software through any available interface—GUIs, code, MCP, and APIs—and selects the most suitable interface per task, unlike most agentic models trained for only one interface type.
Ver el momento de apoyo · Párrafo 9
Agentic Task Factory produces ~10,000 verifiable tasks
The internal Agentic Task Factory generates interactive environments and verifiable tasks from documentation alone—including screenshots and open-source software—and has produced about 10,000 tasks across web apps, MCP servers, desktop environments, and hybrid GUI/MCP environments.
Ver el momento de apoyo · Párrafo 30

Pasajes clave3

Pasajes atribuidos con contexto para verificarlos. Abra el texto original para comprobar la fuente.

Párrafo 30

training data generation

Agentic Task Factory produces ~10,000 verifiable tasks

Extracto original

Our internal set of agentic pipelines builds interactive environments and verifiable tasks from documentation alone, such as screenshots of real websites or open-source software. So far it has produced about 10,000 tasks across web apps, MCP servers and desktop environments, including hybrid environments that expose the same state through a GUI and MCP.

Párrafo 1

model architecture

Two-size agentic model series

Extracto original

Holo4 is our new series of agentic models. It comes in two sizes: 27B dense and 35B-A3B Mixture of Experts. Both are available on the H Models API. We are also releasing an updated version of Holotron 3: Holotron4 Nano.

Párrafo 9

interface generalization

Unified model for GUI, code, MCP, and API interfaces

Extracto original

Holo4 clicks and types on a screen, writes and runs its own code, and calls MCP or API tools. It uses whichever fits the task. Most agentic models are trained for one interface only: GUI-focused models are blind without a screen, while models that prefer tool calling are stuck in front of an application that has no API. Real work is not siloed that way, and a single business task can require combining these different approaches.

Fuente y metodología

Estas perspectivas enlazan a sus fuentes originales. Las paráfrasis están identificadas y no son citas textuales.

Abrir transcripción o material de origen Reportar un problema