Instructions to use reubk/Molmo2-4B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use reubk/Molmo2-4B-GGUF with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf reubk/Molmo2-4B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf reubk/Molmo2-4B-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf reubk/Molmo2-4B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf reubk/Molmo2-4B-GGUF:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf reubk/Molmo2-4B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf reubk/Molmo2-4B-GGUF:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf reubk/Molmo2-4B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf reubk/Molmo2-4B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/reubk/Molmo2-4B-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use reubk/Molmo2-4B-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "reubk/Molmo2-4B-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "reubk/Molmo2-4B-GGUF",
		"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/reubk/Molmo2-4B-GGUF:Q4_K_M

Ollama
How to use reubk/Molmo2-4B-GGUF with Ollama:
```
ollama run hf.co/reubk/Molmo2-4B-GGUF:Q4_K_M
```

Unsloth Studio

How to use reubk/Molmo2-4B-GGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for reubk/Molmo2-4B-GGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for reubk/Molmo2-4B-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for reubk/Molmo2-4B-GGUF to start chatting

Docker Model Runner
How to use reubk/Molmo2-4B-GGUF with Docker Model Runner:
```
docker model run hf.co/reubk/Molmo2-4B-GGUF:Q4_K_M
```

Lemonade

How to use reubk/Molmo2-4B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull reubk/Molmo2-4B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Molmo2-4B-GGUF-Q4_K_M

List all available models

lemonade list

Atomic Chat

Molmo2 GGUF

I won't be maintaining this model

An attempt at supporting Molmo2-4B on llama.cpp for personal use. This is a vibe coded solution so I am still benchmarking its actual performance and yet to determine best parameters. Language model on its own works fine, but seems to be increasingly lobotomized when mmproj is included. Vision modality in the mmproj requires custom modifications to llama.cpp mtmd code which I am optimizing.

Downloads last month: 238

GGUF

Model size

4B params

Architecture

qwen3

Hardware compatibility

4-bit

8-bit

16-bit

Model tree for reubk/Molmo2-4B-GGUF

Base model

Qwen/Qwen3-4B-Instruct-2507

Finetuned

allenai/Molmo2-4B

Quantized

(4)

this model