Holotron4-30B-A3B

[!IMPORTANT] Holo4 family:

• Holo4-27B: Qwen3.8 dense architecture. BF16, FP8, NVFP4, and Q4 GGUF.
• Holo4-35B-A3B: Qwen3.6 MoE architecture. BF16, FP8, NVFP4, and Q4 GGUF.
• Holotron4-30B-A3B: NemotronH Nano Omni architecture. BF16 [current] and FP8.

Model summary

Holotron4-30B-A3B is a vision-language model (VLM) for Computer Use, built on NVIDIA Nemotron 3 Nano Omni and developed by H Company. Used with the hai-agents harness, it can send screenshots and tool results to the model, then execute its requested clicks, typing, code, and tool calls.

This demo shows Holo4-27B using FreeCAD to build a replica of the Eiffel Tower. More examples in the blog post.

Usage

The harness sends screenshots and tool results to Holotron4, executes the model's requested actions, and sends the results back. It can give the model access to application tools and code execution.

Refer to the documentation for more details about:

• Function calling
• Element localization
• Document OCR

Performance

Holotron4 improves over its base model, Nemotron 3 Nano Omni, on GUI workflows and in environments with MCP tools, APIs, or code sandboxes. Gains are absolute percentage points.

Open-source evaluation traces

For transparency, we share all agent trajectories in the open-source dataset at Hcompany/trajectories.

Training

License

The model is governed by the NVIDIA Open Model Agreement.