unsloth/LTX-2.5-FP8
text-to-video model by unsloth
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.
This is an FP8 / INT8 quantized version of the LTX-2.5 distilled video DiT. Built from the transformer/ of Lightricks/LTX-2.5-Diffusers at revision da0b690960026eab794b8ceaf841233cf7064478 (tensor-identical to ltx-2.5-22b-distilled-transformer-bf16.safetensors in Lightricks/LTX-2.5). FP8 quantizes every linear with at least 512 features. INT8 keeps the audio stream, the audio-video cross attention, the adaLN and timestep projections and the norms in bf16. INT8-ConvRot rotates the inputs of all 480 quantized video linears with a block Hadamard (group 256) before quantizing; the rotation is listed in the file's metadata and applied to the activations at run time. Scores are against the bf16 DiT at the reference distilled settings (1280x704, 121 frames, 24 fps, 8 + 3 two-stage steps, CFG 1), text-to-video and image-to-video, seeds 42 and 7, with the same bf16 text encoder in every run; a repeated bf16 render is bit-identical (LPIPS 0.000). The distilled sampler injects noise every step, so small weight errors move the…
Read the full model card ↗ · Preview checked 2026-10-27T17:18:33.845Z
Inside the original model card — Document outline
- Samples
- What's new in LTX-2.5
- Model family & checkpoints
- Transformers (DiT)
- Other components
- Usage
- Online demo
- Option A — Python (ltx-pipelines)
- Install
- Download weights
- Distilled text-to-video
- Image-to-video
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
unsloth/LTX-2.5-FP8 is a text-to-video model repository published by unsloth on Hugging Face. The source reports the diffusers 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
- diffusers
- Recent downloads (30 days)
- 21,198
- Cumulative likes
- 2
- Hugging Face trending score
- 0
- Reported safetensors parameters
- 18,987,859,200
- Architecture
- Not reported
- License
- other
- Access
- Not gated by Hugging Face
- Created
- 2026-10-13T01:52:47.000Z
- Last modified
- 2026-10-16T12:39:28.000Z
Compatibility and lineage
Reported languages: en
Reported base models: Lightricks/LTX-2.5-Diffusers
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 2026-11-01T06:51:32.159Z. 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