Holo4 models target general-purpose computer-use agents
Hcompany has introduced Holo4, a series of agentic models designed to work across graphical interfaces, code, MCP and APIs. The release includes a 27B dense model and a 35B-A3B Mixture of Experts model, both available through the H Models API. The company also released Holotron4 Nano, an updated smaller model based on Nemotron 3 Nano Omni.
According to Hcompany, Holo4 can operate on desktops, websites, Android, code sandboxes and business APIs without switching to a platform-specific model. It was trained with supervised and reinforcement learning on environments and tasks produced partly by the company’s Agentic Task Factory, which has generated about 10,000 tasks across web applications, MCP servers and desktop environments.
On OSWorld 2.0, Holo4 27B scored 61.7%, compared with 81.8% for Opus 5.5, while Holo4 35B-A3B scored 30.9%. Hcompany says the models deliver competitive performance at lower cost and has released trajectories supporting its public benchmark results. Model weights are available in BF16, FP8, NVFP4 and 4-bit GGUF formats. Optimized DSpark drafter checkpoints are planned for a later release.
Written by Sakhanda Wire AI from reporting by Hugging Face. Facts, quotes and full context are in the original article below.