H Company Releases Holo4 Generalist Computer-Use Agent Models

H Company Releases Holo4 Generalist Computer-Use Agent Models H company has announced Holo4, a suite of agentic models trained to operate across graphical user interfaces, code sandboxes, Model Context Protocol (MCP), and business APIs. Available in dense and mixture-of-experts architectures, the models are designed to execute complex business workflows across multiple platforms. Holo4 is released in 27B dense and 35B-A3B Mixture of Experts sizes, alongside Holotron4 Nano. The models interact through GUIs, code execution, MCP tools, and APIs across desktop, web, Android, and sandboxed environments. On the OSWorld 2.0 benchmark, Holo4 27B scored 61.7% and Holo4 35B-A3B scored 30.9%, trailing frontier closed models while operating at reduced cost and parameter scales. Training combined supervised and reinforcement learning on roughly 10,000 tasks generated by an Agentic Task Factory, supported by a rebuilt execution harness. Cross-Interface Operation Unlike agent models restricted to either purely visual interfaces or API tool calling, Holo4 interacts through multiple modalities depending on the workflow. It can click and type on displays, write and execute code, and make API or MCP calls across desktop operating systems, web interfaces, Android devices, and code sandboxes using a single model. Benchmark Results and Cost Performance On the OSWorld 2.0 desktop control benchmark, Holo4 27B achieved a score of 61.7%, compared to 81.8% for Opus 5.5, while Holo4 35B-A3B reached 30.9%. Both models demonstrated improvements over their Qwen base models and compete on AutomationBench at a lower per-task cost. H company has open-sourced all benchmark trajectory logs for public inspection. Training Pipeline and Execution Harness Holo4 was trained on environments synthesized by an internal Agentic Task Factory, which creates interactive setups and verifiable tasks from documentation and screenshots. Alongside model training, the execution harness was redesigned based on failure analysis from OSWorld 2.0, adding persistent memory to track hundreds of execution steps and direct shell access on the host desktop. Variants and Release Formats In addition to the 27B and 35B-A3B models, H company applied its training stack to Nemotron 3 Nano Omni to produce Holotron4 Nano. Model weights for Holo4 are published on Hugging Face in BF16, FP8, NVFP4, and 4-bit GGUF formats, and are accessible via the H Models API, with DSpark drafter checkpoints scheduled for later release.

H company推出通用计算机使用智能体模型系列Holo4与Holotron4 Nano H company发布全新智能体模型系列Holo4（包含27B密集型与35B-A3B混合专家型），以及基于英伟达Nemotron 3 Nano Omni微调的Holotron4 Nano。该系列模型支持跨GUI、代码、MCP与API多种界面执行真实业务流，在降低参数与成本的同时提升了执行效率。 Holo4提供27B密集模型与35B-A3B MoE模型，同时开源了轻量模型Holotron4 Nano及全部评测轨迹数据。 不同于单一界面的智能体，Holo4能在桌面、网页、安卓、代码沙箱和企业API之间统一调用，自主决定屏幕点击、编写代码或调用工具。 在OSWorld 2.0桌面基准测试中，Holo4 27B取得61.7%的成绩，以更小的参数规模和更低的成本紧追闭源前沿模型。 模型通过监督与强化学习训练，依托Agentic Task Factory生成约1万项任务，并升级了具备长期记忆与桌面Shell的执行Harness。 跨界面操作与基准表现 大多数智能体模型通常局限于GUI或API单一形态，而Holo4可在桌面端、网页端、安卓系统、代码沙箱和业务API中以相同调用方式运行，根据任务灵活结合点击打字、代码编写与MCP工具调用。在OSWorld 2.0测试中，Holo4 27B达到61.7%的分数，35B-A3B达到30.9%，在降低任务单次调用成本的同时显著超越其Qwen基础模型。官方已开源评测中每一步的执行轨迹以供复现。 训练流程与Harness重构 Holo4通过监督学习与强化学习构建，数据主要来自其Agentic Task Factory。该流水线可仅根据截图和文档自动生成约1万项跨Web应用、MCP与桌面环境的互动任务。团队还重构了支持数百步交互的执行Harness，主要改进包括赋予模型能够跟踪数百步状态的可靠记忆，以及直接提供桌面机器上的Shell访问权限。 Holotron4 Nano与模型分发 基于英伟达Nemotron联盟合作，团队将该后训练方案迁移至Nemotron 3 Nano Omni，推出了轻量级模型Holotron4 Nano。目前Holo4各尺寸模型均已上线H Models API，并在Hugging Face提供BF16、FP8、NVFP4和4-bit GGUF等多种格式权重，后续还将发布DSpark投机采样草稿检查点以提升推理速度。

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. Get started now: 🤖 Models: Holo4-27B | Holo4-35B-A3B | Holotron4 Nano 🗂️ Full collection (FP16, FP8, GGUF): Holo4 🎞️ Trajectories: viewer | dataset ⚡ H Models API: quickstart 📝 Full blog post: hcompany.ai/newsroom/holo4 Models built for every interface 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 . Competitive with the frontier, at a fraction of the cost 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. Notes on the cost-performance charts 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. AI that does work 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. 3D modeling · Eiffel tower 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 tapers to 4 mm at height 276. The legs stand apart from the ground up to the first platform, and converge as they rise. Nothing fills the space between them: the tower is open, and you can see straight through it from every side. Three platforms, each a solid square slab centred on the axis: 72 mm across and 4 mm thick at height 57; 40 mm across and 3 mm thick at height 115; 22 mm across and 3 mm thick at height 276. A mast from height 276 to 324, square, 8 mm across at its base tapering to 2 mm at the tip. Every part must be a closed solid with non-zero volume, and no part may fill the space between the legs. Holo4 27B (84 calls, 1.3M tokens) Qwen3.8 27B (60 calls, 1.0M tokens) 3D modeling · H logo Build a 3D model in FreeCAD of the H company logo: a solid filled disc beside a blocky sans-serif capital letter H, both extruded to the same thickness, the two shapes of similar height and set apart so they do not overlap, with the centre of the disc level with the middle of the H. Colour both shapes black. Holo4 27B (94 calls, 1.5M tokens) Qwen3.8 27B (118 calls, 1.9M tokens) Game design · Pac-Man Build a Pac-Man-style game in Godot and leave it running. A rectangular maze of walls laid out on a grid, with pellets filling every open corridor. A player marker moves continuously along the corridors, eating each pellet it passes over and scoring a point for it. Three ghosts move through the same corridors and chase the player. If a ghost catches the player, the player loses a life and everything resets to its starting position. Score and lives are drawn on screen. No one is going to play this. The player drives itself with a simple heuristic: at each junction it heads toward the nearest pellet, unless a ghost is close, in which case it moves away from the ghost. The game must run unattended and indefinitely, with no keyboard input at all. When it works, start the game and leave it playing. Holo4 27B (68 calls, 2.4M tokens, 268 lines) Qwen3.8 27B (197 calls, 11.4M tokens, 327 lines) How we built Holo4 Agentic task factory 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. Training Harness Alongside training, we rebuilt our harness, the loop that executes the model's actions and manages its context over hundreds of steps, using feedback from agentic performance on OSWorld 2.0. Agents tagged why each task failed and engineers reviewed their fixes. The largest changes were giving the agent a reliable memory that can keep track of hundreds of steps, and a shell on the desktop machine itself. Opus 5 (70.2%) and GPT-5.6 Sol (66.2%) use max-effort partial rewards on the v2026.08.08 offline set from OpenAI's launch chart , as in the cost-performance plot. Other reference scores come from model cards and the official leaderboard. Task releases, subsets and harnesses vary. Holotron4 Nano Our post-training stack is designed to adapt to new foundation models and produce agents that generalize across interfaces and environments. As a member of the NVIDIA Nemotron Coalition , we applied our latest stack to the Nemotron 3 Nano Omni model as a follow-up to Holotron 3. The same recipe turns Nemotron 3 Nano Omni into Holotron4 Nano, a generalist agentic model that significantly improves over the base model on GUI workflows and in environments exposing MCP, APIs or coding sandboxes. Gains are absolute percentage-point improvements over Nemotron 3 Nano Omni. These gains show that our recipe transfers well and can turn a generalist model into an agentic expert. Nothing in it is size-specific. Run it yourself Both sizes are available today on the H Models API . Weights are on Hugging Face in BF16, FP8, NVFP4 and 4-bit GGUF, next to our small model, Holotron4 Nano . We will release optimized DSpark drafter checkpoints in the coming days to further accelerate inference.