Downloads · 30 days
91
40% of all-time downloads
Deadshot699/ltx-2.5-gemma4-12b-comfy-nvfp4
ltx-2.5-gemma4-12b-comfy-nvfp4 is a machine learning model from Deadshot699. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as other.
ComfyUI-native NVFP4 quantization of the Gemma-4 12B text encoder used by Lightricks/LTX-2.5.
Downloads · 30 days
91
40% of all-time downloads
All-time downloads
230
Public
Repo size
10.6 GB
Likes
10
Public
Click a slice to open those files.
.safetensors10.6 GB · 100%
From the Hugging Face model README
ComfyUI-native NVFP4 quantization of the Gemma-4 12B text encoder used by Lightricks/LTX-2.5.
gemma4-12b-with-proj-ltx-2.5-nvfp4.safetensors
This checkpoint was quantized from the official LTX-2.5 BF16 text encoder:
gemma4-12b-with-proj-ltx-2.5-bf16.safetensors
It is intended as a drop-in replacement for the LTX-2.5 Gemma text encoder in ComfyUI.
The checkpoint uses a mixed-precision layout: the heavy Gemma decoder Linear weights are stored as Comfy-native NVFP4 while embeddings, normalization layers, vision components, and LTX-specific projection layers remain at their source precision.
The model was not retrained or fine-tuned.
Quantized using Comfy-Org/comfy-quants.
The following decoder matrices were converted to NVFP4:
self_attn.q_projself_attn.k_projself_attn.v_proj on sliding-attention layersself_attn.o_projmlp.gate_projmlp.up_projmlp.down_projGemma-4 12B has 48 decoder layers with eight global-attention layers:
5, 11, 17, 23, 29, 35, 41, 47
Those global-attention layers reuse K as V and therefore do not contain a
separate v_proj.weight.
Total NVFP4 matrices: 328.
Place the file in:
ComfyUI/models/text_encoders/
Then select:
gemma4-12b-with-proj-ltx-2.5-nvfp4.safetensors
in the same LTX-2.5 text encoder loader you normally use.
No other workflow changes should be required.
Tested successfully with LTX-2.5 in ComfyUI.
In testing, the NVFP4 encoder:
These are practical observations rather than a formal benchmark.
Native NVFP4 execution is intended for compatible NVIDIA Blackwell hardware with an up-to-date ComfyUI / comfy-kitchen stack.
Behavior on other hardware may differ depending on the available fallback path.
This is a community-made quantized derivative of LTX-2.5 and is subject to the LTX-2.x Community License Agreement.
This is not an official Lightricks or Comfy-Org release.