Instructions to use Hcompany/Holo4-27B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Hcompany/Holo4-27B with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="Hcompany/Holo4-27B")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("Hcompany/Holo4-27B")
model = AutoModelForMultimodalLM.from_pretrained("Hcompany/Holo4-27B", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Hcompany/Holo4-27B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Hcompany/Holo4-27B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Hcompany/Holo4-27B",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/Hcompany/Holo4-27B

SGLang

How to use Hcompany/Holo4-27B with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "Hcompany/Holo4-27B" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Hcompany/Holo4-27B",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "Hcompany/Holo4-27B" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Hcompany/Holo4-27B",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use Hcompany/Holo4-27B with Docker Model Runner:
```
docker model run hf.co/Hcompany/Holo4-27B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Holo4-27B

Holo4 family:

Holo4-27B: Qwen3.8 dense architecture. BF16 [current], 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 and FP8.

Model summary

Holo4-27B is a vision-language model (VLM) for Computer Use, built on Qwen3.8-27B 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.

Specification	Value
Parameters	27B dense
Maximum context length in config	262,144 tokens
Model type	Visual Language Model (VLM)
Architecture	Qwen3.8 dense
Interfaces	Graphical interface, code, and tool calls
Target environments	Web, desktop, and mobile

Holo4 uses FreeCAD to build a replica of the Eiffel Tower. More examples in the blog post.

Prompt

Build a 3D Eiffel Tower in FreeCAD at a scale of 1 mm per metre. Center it on the origin and align it with the X and Y axes. Its plan must stay square at every height. The distance from the center to each 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. Connect these widths with a smooth curve that narrows quickly near the base and more slowly near the top.

Make four separate, identical square legs, one in each quadrant. Their outer corners follow that curve, and each leg narrows from 14 mm across at ground level to 4 mm at height 276. Leave the space between the legs open. Add centered square platforms measuring 72 mm by 72 mm by 4 mm at height 57, 40 mm by 40 mm by 3 mm at height 115, and 22 mm by 22 mm by 3 mm at height 276. Add a square mast from height 276 to 324, tapering from 8 mm across to 2 mm across. Make every component a closed solid with nonzero volume, without filling the space between the legs.

Performance

Holo4 models improve significantly over their Qwen base models. On OSWorld, Holo4-27B scores 85.2% at $0.08 per task. We also evaluate them on Agentic Task Factory, a set of held-out business workflows across web, desktop, and MCP tools.

Benchmark results

Read the blog post for more tables about the benchmark results.

Pareto plots

These plots compare benchmark scores with cost per task. On OSWorld 2.0, Holo4-27B scores 61.7% at $1.22 per task, and Holo4-35B-A3B scores 30.9% at $0.61 per task.

On AutomationBench, Holo4-27B scores 45.4% at $0.05 per task, and Holo4-35B-A3B scores 34.5% at $0.02 per task.

Open-source evaluation traces

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

Usage

The harness sends screenshots and tool results to Holo4, 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:

Training

License

The model weights are available under the Non-commercial (CC BY-NC 4.0) license. This model is built on Qwen3.8-27B, which Alibaba Cloud releases under the Apache License 2.0. The repository includes both licenses.