rockerBOO/ltx-2.5-nvfp4-convrot
text-to-video model by rockerBOO
Older snapshot: check the original source for current information.
From the publisher
Model card & documentation
Source previewRead the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.
Quantized version of Lightricks' LTX-2.5 (22B audio-video diffusion transformer) for ComfyUI, using NVFP4 for most weights and INT8+ConvRot for attention — smaller and faster than the bf16 original with minimal quality loss. Unlike Lightricks' own official quants, blocks 0, 1, 46 and 47 are kept full bf16 precision here. Only the transformer is requantized here. Grab the VAEs and text encoders straight from Lightricks/LTX-2.5 and Comfy-Org/gemma-4 — those are used as-published, not touched by us. Blackwell GPU (SM >= 10.0/12.0) required for inference — RTX 50-series, B100/B200. Same as our other NVFP4 releases. LTX-2 Community License Agreement (included in this repo), inherited from Lightricks/LTX-2.5. No quantization was run ourselves for this file — it's spliced together from tensors in Lightricks' own two official pre-quantized releases, since both already quantize the same tensor set we wanted (verified against the real safetensors headers, not assumed): tensors (INT8+ConvRot) and everything Lightricks itself never…
Read the full model card ↗ · Preview checked 2026-10-29T07:42:52.175Z
Inside the original model card — Document outline
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Links from the model card
References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.
Documentation belongs to its respective authors. Reported project/model license: other. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
rockerBOO/ltx-2.5-nvfp4-convrot is a text-to-video model repository published by rockerBOO on Hugging Face. The source reports the diffusion-single-file library.
This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.
Model facts
- Task
- text-to-video
- Library
- diffusion-single-file
- Recent downloads (30 days)
- 2,994
- Cumulative likes
- 3
- Hugging Face trending score
- 0
- Reported safetensors parameters
- Not reported
- Architecture
- Not reported
- License
- other
- Access
- Not gated by Hugging Face
- Created
- 2026-08-11T18:32:01.000Z
- Last modified
- 2026-08-11T22:32:55.000Z
Compatibility and lineage
Language coverage was not reported.
Reported base models: Lightricks/LTX-2.5
Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.
Use and evaluate
Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.
No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.
Source and freshness
Source: Hugging Face Hub. Metadata observed 2026-09-29T06:39:07.699Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.
Related models
QuantStack/Wan2.2-TI2V-5B-GGUF
QuantStack/Wan2.2-T2V-A14B-GGUF