Az H company bemutatta a Holo4 ágensmodell-sorozatot, amely két méretben, egy 27 milliárd paraméteres sűrű és egy 35 milliárdos MoE változatban érhető el. A modellek különlegessége, hogy nemcsak egyféle felületre korlátozódnak, hanem egyszerre képesek grafikus kezelőfelületeken, kódokon, MCP-n és API-kon keresztül is irányítani a szoftvereket. Az új modellek mellett a fejlesztők kiadták a kisebb méretű Holotron4 Nano változatot is.
A fejlesztés során a modelleket több mint 10 000 feladatot tartalmazó környezetben tanították, így kiemelkedően teljesítenek a komplex munkafolyamatokban. A bemutatók alapján a Holo4 képes 3D-s modelleket tervezni FreeCAD-ben, vagy akár egy működő Pac-Man játékot is lefejleszteni Godot-ban, teljesen önállóan. A modellek asztali gépeken, weben, Androidon és kódhomokozókban is ugyanúgy futtathatók.
A modellek súlyai már ingyenesen letölthetők a Hugging Face felületéről, valamint elérhetők az H Models API-n keresztül is. A Holo4 a teszteken a piacvezető zárt modellek szintjét közelíti meg, de töredék áron és jóval kisebb méretben kínálja ugyanezt a teljesítményt.
Az eredeti szöveg (Hugging Face)
Models built for every interface Competitive with the frontier, at a fraction of the cost AI that does work 3D modeling · Eiffel tower 3D modeling · H logo Game design · Pac-Man How we built Holo4 Agentic task factory Training Harness Holotron4 Nano Run it yourself
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.
Holo4 builds on our previous model and interacts with software through any available interface: GUIs, code, MCP and APIs. It scores well on academic benchmarks, but we built it for real business workflows. It was trained through supervised and reinforcement learning on a large set of environments and tasks, including those generated by our Agentic Task Factory.
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.
Holo4 runs on desktops, on the web, on Android, in a code sandbox and against business APIs. It is the same model in each case and it is called the same way. You do not need to select a different model for each platform.
Holo4 models improve significantly over their Qwen base. Holo4 trails only the strongest closed models on long workflows: on OSWorld 2.0, Holo4 27B scores 61.7% against 81.8% for Opus 5.5, and Holo4 35B-A3B reaches 30.9%. However, it does so with orders of magnitude fewer parameters and at a much lower cost. We open-source every trajectory behind our scores on public benchmarks: replay each step at trajectories.hcompany.ai or download them from Hugging Face.
On the hardest academic benchmarks for desktop control (OSWorld 2.0) and API use (AutomationBench), Holo4 competes with frontier models at a much lower cost per task.
OSWorld 2.0. Costs are estimated from the input and output tokens of each agentic run. Holo4 is priced at H Models API rates (single run). Qwen3.8 27B: model card score, cost from the tokens of our run at Alibaba Cloud list prices. Qwen3.6 35B-A3B: single run in our harness, at Alibaba Cloud list prices with cache hits at 20% of the input price. OpenAI launch data supplies the GPT and Opus effort sweeps; other closed and open-weight points use the official OSWorld 2.0 leaderboard. Releases, harnesses and task subsets differ. The line connects non-dominated score and cost pairs among the closed models; Holo4 is excluded.
AutomationBench. Holo4, Qwen3.8 27B and Qwen3.6 35B-A3B: AutomationBench v1.0.6, scores and costs measured in our internal harness. Other models: public-set scores from the AutomationBench README, cost per task from the official leaderboard, which runs on the private set. We will report Holo4 on the private set once it is evaluated.
Trained on environments and tasks from our Agentic Task Factory, Holo4 models excel on professional software. The examples below show Holo4 27B alongside Qwen3.8 27B, its base model. Same prompt and harness for both models.
Build a 3D model of the Eiffel Tower in FreeCAD, at a scale of 1 mm to 1 metre, centred on the origin and aligned to the X and Y axes. Work to this design.
The tower is square in plan at every height, never round. Its half-width, measured from the central axis out to the corner, is 62.5 mm at ground level, 32.5 mm at height 57, 17.5 mm at height 115, and 9.35 mm at height 276. Between those heights the half-width follows a smooth curve that falls steeply near the ground and gently higher up, never a straight line.
Four identical legs, one per quadrant, each a square column whose outer corner follows that profile. Each leg is 14 mm across at the ground and tap
