---
license: other
license_name: ltx-2-community-license-agreement
license_link: https://huggingface.co/Lightricks/LTX-2.3/blob/main/LICENSE
library_name: diffusers
pipeline_tag: image-text-to-video
tags:
- comfyui
- safetensors
base_model:
- Lightricks/LTX-2.3
base_model_relation: quantized
---

14/04: uploaded fp8mixed an nvfp4mixed of LTX-2.3-distilled-1.1

---

16/03: Lightricks released an official [dev-nvfp4](https://huggingface.co/Lightricks/LTX-2.3-nvfp4/blob/main/ltx-2.3-22b-dev-nvfp4.safetensors) and [distilled-fp8](https://huggingface.co/Lightricks/LTX-2.3-fp8/blob/main/ltx-2.3-22b-distilled-fp8.safetensors)

---

09/03: all formats of both dev & distilled in nvfp4, nvfp4mixed, fp8, and fp8mixed done. 

---

07/03: ⚠️ make sure your torch (>=2.10) & cuda (>=13.0) are up to date, otherwise you won't see a speed boost using nvfp4, may even be slower ⚠️ 

--- 

05/03: Lightricks released an official [dev-fp8](https://huggingface.co/Lightricks/LTX-2.3-fp8/blob/main/ltx-2.3-22b-dev-fp8.safetensors), probably better to use it instead of mine.

---

Various formats of [LTX-2.3](https://huggingface.co/Lightricks/LTX-2.3), all created from official BF16 versions. 
Made with [Silveroxides/convert_to_quant](https://github.com/silveroxides/convert_to_quant) script:

- fp8mixed
- fp8
- nvfp4mixed
- nvfp4


- non-calibrated / nc: direct conversion without SVD optimization
- mixed: keep some weights in native format (embeddings, norm, bias, etc), same exclusion strategy as Lightricks
  
---

## run time

config: Windows 11, Nvidia 5090, torch2.10+cu130, SageAttention2.2

- 8 steps, CFG 1
- default sampler/scheduler
- 960 x 544p, 121 frames, 24 fps
- x2 spatial upscale 
- 4 refining steps

| format           | distilled | dev + distill lora |
|------------------|-----------|--------------------|
| nvfp4            | 54s       | 57s                |
| nvfp4-mixed      | 57s       | 59s                |
| fp8 (mine)       | 61s       | 61s                | 
| fp8 (Lightricks) | TODO      | 63s                |
| bf16             | 87s       | 91s                |

Hot run, prompt already processed.

Smaller formats look a bit "fuzzy" around the edges in the outputs, but motion, audio, and lighting are still looking good.