Instructions to use allenai/Molmo2-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use allenai/Molmo2-8B with Transformers:

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

pipe = pipeline("image-text-to-text", model="allenai/Molmo2-8B", trust_remote_code=True)
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("allenai/Molmo2-8B", trust_remote_code=True)
model = AutoModelForMultimodalLM.from_pretrained("allenai/Molmo2-8B", trust_remote_code=True, 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 allenai/Molmo2-8B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "allenai/Molmo2-8B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "allenai/Molmo2-8B",
		"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/allenai/Molmo2-8B

SGLang

How to use allenai/Molmo2-8B 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 "allenai/Molmo2-8B" \
    --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": "allenai/Molmo2-8B",
		"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 "allenai/Molmo2-8B" \
        --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": "allenai/Molmo2-8B",
		"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 allenai/Molmo2-8B with Docker Model Runner:
```
docker model run hf.co/allenai/Molmo2-8B
```

Molmo2-8B

Commit History

Jan 23

01:02
Update README.md

roTripathi

Verified signature
e28fa28

Dec 23, 2025

08:03
Update README.md (#2)⁠

jamesp-allenai

Verified signature
0df20bf
06:38
Update README.md

sanghol

Verified signature
72185cc

Dec 16, 2025

04:39
Update README.md

sanghol

Verified signature
389c684
03:58
Update README.md

sanghol

Verified signature
25c883b
02:42
Delete MainFig_WIP_8.png

roTripathi

Verified signature
9a7c96c
02:06
Update README.md

roTripathi

Verified signature
4ff388a
01:48
highlight specific model

roTripathi

Verified signature
292ed51
01:37
update license

roTripathi

Verified signature
acff1d3
01:29
Add multi image pointing

roTripathi

Verified signature
59403f8
01:19
Add tracking example

roTripathi

Verified signature
ef4c117
00:55
add pointing and general QA examples

roTripathi

Verified signature
ec6e58f

Dec 15, 2025

19:57
Update README.md

roTripathi

Verified signature
1b4ced5
19:34
Update README.md

roTripathi

Verified signature
38e9b34
19:25
upload main capability image

roTripathi

Verified signature
2fc09ef
18:58
Update README.md

roTripathi

Verified signature
8d9af77
18:57
Create README.md⁠

roTripathi

Verified signature
c0c2b8f
18:36
Upload molmo_2_logo_RGB.png⁠

roTripathi

Verified signature
db8d279

Dec 14, 2025

23:02
Upload Molmo2-8B

sanghol

Verified signature
2d4f65a
22:59
initial commit

sanghol

Verified signature
97369a1

Commit History

Jan 23

Update README.md

Dec 23, 2025

Update README.md (#2)⁠

Update README.md

Dec 16, 2025

Update README.md

Update README.md

Delete MainFig_WIP_8.png

Update README.md

highlight specific model

update license

Add multi image pointing

Add tracking example

add pointing and general QA examples

Dec 15, 2025

Update README.md

Update README.md

upload main capability image

Update README.md

Create README.md⁠

Upload molmo_2_logo_RGB.png⁠

Dec 14, 2025

Upload Molmo2-8B

initial commit