An fp8_e4m3fn conversion of the text encoder at https://huggingface.co/Comfy-Org/ltx-2/blob/main/split_files/text_encoders/gemma_3_12B_it.safetensors, which is used for [LTX-2](https://huggingface.co/Lightricks/LTX-2)

[gemma_3_12B_it_fp8_e4m3fn.safetensors](https://huggingface.co/GitMylo/LTX-2-comfy_gemma_fp8_e4m3fn/blob/main/gemma_3_12B_it_fp8_e4m3fn.safetensors) - The fp8 converted text encoder from comfy, goes in `CLIP` folder  
[gemma_3_12B_it_nvfp4_uncalibrated.safetensors](https://huggingface.co/GitMylo/LTX-2-comfy_gemma_fp8_e4m3fn/blob/main/gemma_3_12B_it_nvfp4_uncalibrated.safetensors) - The nvfp4 converted (using comfyui kitchen utils) text encoder from comfy, goes in `CLIP` folder. **NOTE: You will get warnings in the console, these can be ignored and will not affect your generation.**  
[ltx-2-19b-dev-fp4_projections_only.safetensors](https://huggingface.co/GitMylo/LTX-2-comfy_gemma_fp8_e4m3fn/blob/main/ltx-2-19b-dev-fp4_projections_only.safetensors) - Extracted projections from LTX-2 model to allow loading with DualClipLoader node, goes in `CLIP` folder  
[ltx-2-19b-dev-fp4_video_vae.safetensors](https://huggingface.co/GitMylo/LTX-2-comfy_gemma_fp8_e4m3fn/blob/main/ltx-2-19b-dev-fp4_video_vae.safetensors) - The video vae, can be loaded with `VaeLoader` node, goes in `VAE` folder  
~~[ltx-2-19b-dev-fp4_vocoder.safetensors](https://huggingface.co/GitMylo/LTX-2-comfy_gemma_fp8_e4m3fn/blob/main/ltx-2-19b-dev-fp4_vocoder.safetensors) - The vocoder model, not useful separately currently~~  
For audio vae, use Kijai's audio vae upload [LTX2_audio_vae_bf16.safetensors](https://huggingface.co/Kijai/LTXV2_comfy/blob/main/VAE/LTX2_audio_vae_bf16.safetensors), the one in this repo only contains the vocoder, but the audio vae is also needed. There was an oversight due to ComfyUI caching when it shouldn't.

## Usage
When using a ComfyUI workflow which uses the original fp16 gemma 3 12b it model, simply select the text encoder from here instead.

~~Right now ComfyUI memory offloading seems to have issues with the text encoder loaded by the LTX-2 text encoder loader node, for now as a workaround (If you're getting an OOM error) you can launch ComfyUI with the `--novram` flag. This will slightly slow down generations so I recommend reverting this when a fix has been released.~~  
--lowvram isn't needed if using the DualClipLoader, as it can be set to use cpu only.

## Usage with DualClipLoader (with projections)
Use the vanilla ComfyUI DualClipLoader node, and as the clip models select the `gemma_3_12B_it_fp8_e4m3fn.safetensors` and `ltx-2-19b-dev-fp4_projections_only.safetensors` from this repo. Now replace the LTXV Audio Text Encoder Loader node with the DualClipLoader node.