Video models · Lightricks
LTX-Video 13B 0.9.8 (distilled)
- Backbone
- 13.0B
- Native output
- 1216×704, 121 frames
- Default steps
- 8
- License
- ltx-video-open-weights
- Released
- 2025-07
How to run it
Original weights · Hugging Face
Full-precision files from Lightricks, for fine-tuning, vLLM, Transformers, Diffusers or ComfyUI.
huggingface.co/Lightricks/LTX-Video-0.9.8-13B-distilled (opens in a new tab)
Official repo · GitHub
Reference code, inference scripts and docs from Lightricks. The weights themselves download from Hugging Face.
github.com/Lightricks/LTX-Video (opens in a new tab)
git clone https://github.com/Lightricks/LTX-VideoMemory needed
Peak GPU memory at the native output size. Offloading moves the text encoder, or the whole pipeline, to system RAM between steps.
| Precision | Everything on GPU | Text encoder offloaded | Sequential offload | Download |
|---|---|---|---|---|
FP16 | 47.9 GB | 38.4 GB | 20.6 GB | Original weights (opens in a new tab) |
FP8 | 30.1 GB | 25.4 GB | 16.1 GB | Original weights (opens in a new tab) |
Components
- Backbone: 13.04B
- VAE: 0.4B
- T5-XXL: 4.76B
Best hardware for LTX-Video 13B 0.9.8 (distilled)
The least expensive GPU in our catalog that runs it without offloading is the AMD Radeon RX 7900 XT (launch price $899) at FP8.
| Grade · points | Hardware | Precision | Memory | Time per output | Fit |
|---|---|---|---|---|---|
| 82 ptsGreat (A) · 82 of 100 points: Model quality 30.0/45, Memory fit 23.0/25, Speed 15.0/15, Memory use 15.0/15 | NVIDIA GeForce RTX 5090 | FP8 | 30.1 GB / 32.0 GB | 45 s | Tight fit |
| 82 ptsGreat (A) · 82 of 100 points: Model quality 30.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 11.5/15 | AMD Ryzen AI Max+ 395 (128 GB) | FP16 | 47.9 GB / 96.0 GB | 1.9 min | Runs well |
| 82 ptsGreat (A) · 82 of 100 points: Model quality 30.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 11.5/15 | NVIDIA RTX PRO 6000 Blackwell | FP16 | 47.9 GB / 96.0 GB | 44 s | Runs well |
| 80 ptsGreat (A) · 80 of 100 points: Model quality 30.0/45, Memory fit 25.0/25, Speed 11.3/15, Memory use 14.5/15 | Apple M4 Max (64 GB) | FP8 | 30.1 GB / 48.0 GB | 5.3 min | Runs well |
| 80 ptsGreat (A) · 80 of 100 points: Model quality 30.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 9.6/15 | NVIDIA GB10 (128 GB) | FP16 | 47.9 GB / 115 GB | 2.1 min | Runs well |
| 78 ptsGreat (A) · 78 of 100 points: Model quality 30.0/45, Memory fit 25.0/25, Speed 8.7/15, Memory use 15.0/15 | Apple M4 Pro (48 GB) | FP8 | 30.1 GB / 36.0 GB | 8.9 min | Runs well |
| 78 ptsGreat (A) · 78 of 100 points: Model quality 30.0/45, Memory fit 25.0/25, Speed 9.1/15, Memory use 14.5/15 | Apple M1 Max (64 GB) | FP8 | 30.1 GB / 48.0 GB | 8.1 min | Runs well |
| 77 ptsGreat (A) · 77 of 100 points: Model quality 30.6/45, Memory fit 25.0/25, Speed 10.7/15, Memory use 11.5/15 | Apple M4 Max (128 GB) | FP16 | 47.9 GB / 96.0 GB | 5.9 min | Runs well |
| 72 ptsGreat (A) · 72 of 100 points: Model quality 30.0/45, Memory fit 25.0/25, Speed 13.1/15, Memory use 4.8/15 | Apple M2 Ultra (192 GB) | FP8 | 30.1 GB / 144 GB | 3.9 min | Runs well |
| 71 ptsGood (B) · 71 of 100 points: Model quality 30.0/45, Memory fit 12.0/25, Speed 15.0/15, Memory use 15.0/15 | AMD Radeon RX 7900 XTX | FP8 | 16.1 GB / 24.0 GB | 78 s | Runs well |
Estimates come from published hardware specs and our open formulas, not from running the model on your machine. Real speed varies with runtime, drivers and settings. Numbers marked “Measured” come from a linked benchmark.