Instructions to use Hansda/ScreenVLM-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use Hansda/ScreenVLM-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 Hansda/ScreenVLM-GGUF:F16 # Run inference directly in the terminal: llama cli -hf Hansda/ScreenVLM-GGUF:F16
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf Hansda/ScreenVLM-GGUF:F16 # Run inference directly in the terminal: llama cli -hf Hansda/ScreenVLM-GGUF:F16
Build from source code
git clone https://github.com/ggml-org/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-app # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama serve -hf Hansda/ScreenVLM-GGUF:F16 # Run inference directly in the terminal: ./build/bin/llama cli -hf Hansda/ScreenVLM-GGUF:F16
Use Docker
docker model run hf.co/Hansda/ScreenVLM-GGUF:F16
- Llama new
- LM Studio
- Jan
- vLLM
How to use Hansda/ScreenVLM-GGUF with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Hansda/ScreenVLM-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": "Hansda/ScreenVLM-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/Hansda/ScreenVLM-GGUF:F16
- Ollama
How to use Hansda/ScreenVLM-GGUF with Ollama:
ollama run hf.co/Hansda/ScreenVLM-GGUF:F16
- Unsloth Desktop
- Docker Model Runner
How to use Hansda/ScreenVLM-GGUF with Docker Model Runner:
docker model run hf.co/Hansda/ScreenVLM-GGUF:F16
- Lemonade
How to use Hansda/ScreenVLM-GGUF with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull Hansda/ScreenVLM-GGUF:F16
Run and chat with the model
lemonade run user.ScreenVLM-GGUF-F16
List all available models
lemonade list
- Atomic Chat
Download conversion-metadata.json from Hansda/ScreenVLM-GGUF: direct link, hf CLI and curl.
- Browser
- Download file 444 Bytes
-
https://huggingface.co/Hansda/ScreenVLM-GGUF/resolve/main/conversion-metadata.json
- Command line
-
hf download hf://Hansda/ScreenVLM-GGUF/conversion-metadata.json
-
curl -L -o conversion-metadata.json https://huggingface.co/Hansda/ScreenVLM-GGUF/resolve/main/conversion-metadata.json
444 Bytes
| { | |
| "general.name": "ScreenVLM ScreenParse-v2 GGUF", | |
| "general.description": "Modified from docling-project/ScreenVLM 78df0cc8498bbea1a03eb2816056fc0a76d2f63d: converted to GGUF F16, with independently derived Q8_0 and Q4_K_M decoder variants. No training; source Apache-2.0 declaration retained. See CHANGES.md.", | |
| "general.source.repo_url": "https://huggingface.co/docling-project/ScreenVLM/tree/78df0cc8498bbea1a03eb2816056fc0a76d2f63d" | |
| } | |