Instructions to use GrootTeam/Groot-19B-A3B-261023 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use GrootTeam/Groot-19B-A3B-261023 with Transformers:

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

pipe = pipeline("image-text-to-text", model="GrootTeam/Groot-19B-A3B-261023")
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("GrootTeam/Groot-19B-A3B-261023")
model = AutoModelForMultimodalLM.from_pretrained("GrootTeam/Groot-19B-A3B-261023", 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 GrootTeam/Groot-19B-A3B-261023 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "GrootTeam/Groot-19B-A3B-261023"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "GrootTeam/Groot-19B-A3B-261023",
		"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/GrootTeam/Groot-19B-A3B-261023

SGLang

How to use GrootTeam/Groot-19B-A3B-261023 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 "GrootTeam/Groot-19B-A3B-261023" \
    --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": "GrootTeam/Groot-19B-A3B-261023",
		"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 "GrootTeam/Groot-19B-A3B-261023" \
        --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": "GrootTeam/Groot-19B-A3B-261023",
		"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 GrootTeam/Groot-19B-A3B-261023 with Docker Model Runner:
```
docker model run hf.co/GrootTeam/Groot-19B-A3B-261023
```

Wonderful

by hamzah0asadullah - opened 10 days ago

Discussion

hamzah0asadullah

10 days ago

The model is actually able to follow my system prompt (which is quite lengthy; it's more a Markdown document).
I was waiting for Qwen4 because until now only Qwen3.8 27B integrated well with my VRAM (20GB) constraints while being usable (it's very, very slow though).

Your model is fast, fits the full 256k context in my VRAM (GGUF Q4_K_M, KV-cache not quantized), and achieves the same tasks as Q3.8 27B while just generally feeling more human (e.g. following adjectives outlined in my system prompt). Tool use I observed until now is unflawed.

Have a wonderful day.

urtuuuu

8 days ago

•

edited 8 days ago

yeah, can confirm, i always use same test questions with all models, so i can clearly tell if it's good or not. Haven't tested it in agentic coding yet, but looks promising.
But i also tested SVG quality, and it's really bad.

GrootTeam

Owner about 4 hours ago

Thank you for the detailed feedback, we're really glad Groot-19B works well with your long system prompt, the 256K context and your VRAM setup. Please keep sharing any issues you run into.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment