Instructions to use unsloth/LTX-2-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Local Apps Settings
- Unsloth Studio
How to use unsloth/LTX-2-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 unsloth/LTX-2-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 unsloth/LTX-2-GGUF to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for unsloth/LTX-2-GGUF to start chatting
Load model with FastModel
pip install unsloth from unsloth import FastModel model, tokenizer = FastModel.from_pretrained( model_name="unsloth/LTX-2-GGUF", max_seq_length=2048, )
UD and iQ quants for the distilled model?
Thanks!
Hello, which distilled model are you referring to? Thanks :)
Hello, which distilled model are you referring to? Thanks :)
https://huggingface.co/Lightricks/LTX-2/tree/main The distilled model from here, though it seems like kijai hasn't uploaded the transformer-only bf16 variants of that model https://huggingface.co/Kijai/LTXV2_comfy/tree/main/diffusion_models , there are GGUFs https://huggingface.co/Kijai/LTXV2_comfy/blob/main/diffusion_models/ltx-2-19b-distilled_Q4_K_M.gguf though no UD/iQ quants.
Edit: someone has made a bf16 transformer only safetensors variant for the distilled model here https://huggingface.co/vantagewithai/LTX-2-Split/tree/main/model
Hello, which distilled model are you referring to? Thanks :)
Now its also up on Kijai's repo.
We need your distilled quants!
thx bro now is working and how can i make video to video or photo to video make longer video?
