Instructions to use vidfom/Ltx-3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- llama-cpp-python
How to use vidfom/Ltx-3 with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="vidfom/Ltx-3", filename="ComfyUI/models/text_encoders/gemma-3-12b-it-qat-UD-Q4_K_XL.gguf", )
llm.create_chat_completion( messages = "No input example has been defined for this model task." )
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- llama.cpp
How to use vidfom/Ltx-3 with llama.cpp:
Install from brew
brew install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf vidfom/Ltx-3:UD-Q4_K_XL # Run inference directly in the terminal: llama-cli -hf vidfom/Ltx-3:UD-Q4_K_XL
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf vidfom/Ltx-3:UD-Q4_K_XL # Run inference directly in the terminal: llama-cli -hf vidfom/Ltx-3:UD-Q4_K_XL
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 vidfom/Ltx-3:UD-Q4_K_XL # Run inference directly in the terminal: ./llama-cli -hf vidfom/Ltx-3:UD-Q4_K_XL
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 vidfom/Ltx-3:UD-Q4_K_XL # Run inference directly in the terminal: ./build/bin/llama-cli -hf vidfom/Ltx-3:UD-Q4_K_XL
Use Docker
docker model run hf.co/vidfom/Ltx-3:UD-Q4_K_XL
- LM Studio
- Jan
- Ollama
How to use vidfom/Ltx-3 with Ollama:
ollama run hf.co/vidfom/Ltx-3:UD-Q4_K_XL
- Unsloth Studio new
How to use vidfom/Ltx-3 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 vidfom/Ltx-3 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 vidfom/Ltx-3 to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for vidfom/Ltx-3 to start chatting
- Docker Model Runner
How to use vidfom/Ltx-3 with Docker Model Runner:
docker model run hf.co/vidfom/Ltx-3:UD-Q4_K_XL
- Lemonade
How to use vidfom/Ltx-3 with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull vidfom/Ltx-3:UD-Q4_K_XL
Run and chat with the model
lemonade run user.Ltx-3-UD-Q4_K_XL
List all available models
lemonade list
| import os | |
| import configparser | |
| GITHUB_ENDPOINT = os.getenv('GITHUB_ENDPOINT') | |
| def is_git_repo(path: str) -> bool: | |
| """ Check if the path is a git repository. """ | |
| # NOTE: Checking it through `git.Repo` must be avoided. | |
| # It locks the file, causing issues on Windows. | |
| return os.path.exists(os.path.join(path, '.git')) | |
| def get_commit_hash(fullpath): | |
| git_head = os.path.join(fullpath, '.git', 'HEAD') | |
| if os.path.exists(git_head): | |
| with open(git_head) as f: | |
| line = f.readline() | |
| if line.startswith("ref: "): | |
| ref = os.path.join(fullpath, '.git', line[5:].strip()) | |
| if os.path.exists(ref): | |
| with open(ref) as f2: | |
| return f2.readline().strip() | |
| else: | |
| return "unknown" | |
| else: | |
| return line | |
| return "unknown" | |
| def git_url(fullpath): | |
| """ | |
| resolve version of unclassified custom node based on remote url in .git/config | |
| """ | |
| git_config_path = os.path.join(fullpath, '.git', 'config') | |
| if not os.path.exists(git_config_path): | |
| return None | |
| # Set `strict=False` to allow duplicate `vscode-merge-base` sections, addressing <https://github.com/ltdrdata/ComfyUI-Manager/issues/1529> | |
| config = configparser.ConfigParser(strict=False) | |
| config.read(git_config_path) | |
| for k, v in config.items(): | |
| if k.startswith('remote ') and 'url' in v: | |
| if 'Comfy-Org/ComfyUI-Manager' in v['url']: | |
| return "https://github.com/ltdrdata/ComfyUI-Manager" | |
| return v['url'] | |
| return None | |
| def normalize_url(url) -> str: | |
| github_id = normalize_to_github_id(url) | |
| if github_id is not None: | |
| url = f"https://github.com/{github_id}" | |
| return url | |
| def normalize_to_github_id(url) -> str: | |
| if 'github' in url or (GITHUB_ENDPOINT is not None and GITHUB_ENDPOINT in url): | |
| author = os.path.basename(os.path.dirname(url)) | |
| if author.startswith('git@github.com:'): | |
| author = author.split(':')[1] | |
| repo_name = os.path.basename(url) | |
| if repo_name.endswith('.git'): | |
| repo_name = repo_name[:-4] | |
| return f"{author}/{repo_name}" | |
| return None | |
| def get_url_for_clone(url): | |
| url = normalize_url(url) | |
| if GITHUB_ENDPOINT is not None and url.startswith('https://github.com/'): | |
| url = GITHUB_ENDPOINT + url[18:] # url[18:] -> remove `https://github.com` | |
| return url | |