Instructions to use Cinv/cvstudio-models 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 Cinv/cvstudio-models 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 Cinv/cvstudio-models:Q4_K_M # Run inference directly in the terminal: llama cli -hf Cinv/cvstudio-models:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf Cinv/cvstudio-models:Q4_K_M # Run inference directly in the terminal: llama cli -hf Cinv/cvstudio-models:Q4_K_M
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 Cinv/cvstudio-models:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama cli -hf Cinv/cvstudio-models:Q4_K_M
Use Docker
docker model run hf.co/Cinv/cvstudio-models:Q4_K_M
- Llama new
- LM Studio
- Jan
- Ollama
How to use Cinv/cvstudio-models with Ollama:
ollama run hf.co/Cinv/cvstudio-models:Q4_K_M
- Unsloth Desktop
- Docker Model Runner
How to use Cinv/cvstudio-models with Docker Model Runner:
docker model run hf.co/Cinv/cvstudio-models:Q4_K_M
- Lemonade
How to use Cinv/cvstudio-models with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull Cinv/cvstudio-models:Q4_K_M
Run and chat with the model
lemonade run user.cvstudio-models-Q4_K_M
List all available models
lemonade list
- Atomic Chat
CV Studio — copies of the on-device model files
Unchanged copies of the files the CV Studio desktop app downloads for its extra picture / video models, kept so a
customer's download never depends on someone else's repository. Paths: <original repo>/<commit>/<file>; the app
checks every file against the SHA-256 pinned in its code and falls back to the original repository.
| Pack | Model | Licence |
|---|---|---|
| Bộ vẽ ảnh cao cấp | FLUX.2 [klein] 4B (black-forest-labs) GGUF by leejet; Qwen3-4B GGUF by unsloth; FLUX.2 VAE / small decoder | Apache-2.0 |
| Bộ vẽ ảnh chất lượng tối đa | Z-Image-Turbo (Tongyi-MAI) GGUF by leejet; Qwen3-4B-Instruct-2507 GGUF by unsloth; FLUX.1 ae | Apache-2.0 |
| Video AI | FastWan2.2-TI2V-5B (FastVideo) GGUF by Green-Sky; umT5-XXL GGUF by city96; Wan 2.2 VAE; TAEHV taew2_2 (madebyollin, MIT) | Apache-2.0 / MIT |
All rights to the models stay with their authors; see each original repository for its licence text.
- Downloads last month
- -
Hardware compatibility
Log In to add your hardware
3-bit
4-bit
6-bit
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support