Instructions to use bartowski/Qwen2-VL-2B-Instruct-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 bartowski/Qwen2-VL-2B-Instruct-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 bartowski/Qwen2-VL-2B-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf bartowski/Qwen2-VL-2B-Instruct-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 bartowski/Qwen2-VL-2B-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf bartowski/Qwen2-VL-2B-Instruct-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 bartowski/Qwen2-VL-2B-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf bartowski/Qwen2-VL-2B-Instruct-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 bartowski/Qwen2-VL-2B-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf bartowski/Qwen2-VL-2B-Instruct-GGUF:Q4_K_M

Use Docker

docker model run hf.co/bartowski/Qwen2-VL-2B-Instruct-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use bartowski/Qwen2-VL-2B-Instruct-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "bartowski/Qwen2-VL-2B-Instruct-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": "bartowski/Qwen2-VL-2B-Instruct-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/bartowski/Qwen2-VL-2B-Instruct-GGUF:Q4_K_M

Ollama
How to use bartowski/Qwen2-VL-2B-Instruct-GGUF with Ollama:
```
ollama run hf.co/bartowski/Qwen2-VL-2B-Instruct-GGUF:Q4_K_M
```

Unsloth Studio

How to use bartowski/Qwen2-VL-2B-Instruct-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 bartowski/Qwen2-VL-2B-Instruct-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 bartowski/Qwen2-VL-2B-Instruct-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for bartowski/Qwen2-VL-2B-Instruct-GGUF to start chatting

Docker Model Runner
How to use bartowski/Qwen2-VL-2B-Instruct-GGUF with Docker Model Runner:
```
docker model run hf.co/bartowski/Qwen2-VL-2B-Instruct-GGUF:Q4_K_M
```

Lemonade

How to use bartowski/Qwen2-VL-2B-Instruct-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull bartowski/Qwen2-VL-2B-Instruct-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Qwen2-VL-2B-Instruct-GGUF-Q4_K_M

List all available models

lemonade list

Atomic Chat

How much RAM and VRAM does the model require?

by supercharge19 - opened Jan 2, 2025

Discussion

supercharge19

Jan 2, 2025

I tried original model but had problems.
CUDA went out of memory with the 400KB image (which is provided in the code). It asked for 12GB VRAM (tried to allocate 12GB of RAM).

Then I tried to load it 8bits still got the error.

Then I tried loading model without GPU (16GB RAM) and process of reading image got killed. I am going to try with gguf 8bit version now, hopefully this can be used.

bartowski

Owner Jan 2, 2025

It didn't feel like it was that much, but I can run a test locally to see.. Which image are you attempting? Is it this one they share in their GitHub code?

https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg

supercharge19

Jan 3, 2025

Picture of dog and woman. However, I'm able to try with gguf model (not a full model, I guess full model did not fit 3GB VRAM of 1050 laptop), anyway, even with gguf quant 8 it took about 10 minutes and I stopped execution. How long does it take normally to get response?

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