Instructions to use Blockway/Agens-Pilot-Int4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Blockway/Agens-Pilot-Int4 with Transformers:

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

pipe = pipeline("image-text-to-text", model="Blockway/Agens-Pilot-Int4")
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)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("Blockway/Agens-Pilot-Int4")
model = AutoModelForMultimodalLM.from_pretrained("Blockway/Agens-Pilot-Int4", 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=256)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Blockway/Agens-Pilot-Int4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Blockway/Agens-Pilot-Int4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Blockway/Agens-Pilot-Int4",
		"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/Blockway/Agens-Pilot-Int4

SGLang

How to use Blockway/Agens-Pilot-Int4 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 "Blockway/Agens-Pilot-Int4" \
    --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": "Blockway/Agens-Pilot-Int4",
		"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 "Blockway/Agens-Pilot-Int4" \
        --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": "Blockway/Agens-Pilot-Int4",
		"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 Blockway/Agens-Pilot-Int4 with Docker Model Runner:
```
docker model run hf.co/Blockway/Agens-Pilot-Int4
```

Agens-Pilot-Int4

File size: 1,488 Bytes

Agens Pilot
Copyright 2026 BlockWay Link Limited (博睿鏈科有限公司)

This product is developed and released by Blockway (BlockWay Link Limited),
a Hong Kong company — https://blockway.io

Licensed under the Apache License, Version 2.0 (the "License"); you may not
use these files except in compliance with the License. A copy of the License
is provided in the accompanying LICENSE file and at:

    http://www.apache.org/licenses/LICENSE-2.0

Unless required by applicable law or agreed to in writing, software distributed
under the License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR
CONDITIONS OF ANY KIND, either express or implied.

------------------------------------------------------------------------------
Third-party attribution
------------------------------------------------------------------------------

Agens Pilot is a fine-tune of Qwen3.8-27B, developed by the Qwen team at
Alibaba Cloud and released under the Apache License, Version 2.0.

    https://huggingface.co/Qwen/Qwen3.8-27B

Copyright 2026 Alibaba Cloud. The base model's architecture, tokenizer and
pre-/post-trained weights are the work of the Qwen team; Blockway's
contribution is the additional post-training described in the model card
(Cantonese-first behaviour, balanced multi-perspective answers on complex
questions with universal safety retained, and agent-harness tuning).
Modifications to the original weights are indicated by this notice and the
accompanying model card.