Video model · ltx-video
LX LTX-Video 13B requirements
DIT video model · 13B params · 1216×704, 161f (~5s) · released May 2025. Realistic minimum to run: Nvidia GeForce RTX 4090 (24GB) at fp8.
OpenRAIL-M open-weights license; commercial use permitted subject to use-based restrictions.
Backbone size by precision
| Precision | Size |
|---|---|
| fp16 / bf16 | 28.6 GB |
| fp8 (recommended) | 15.7 GB |
Backbone weights only. Peak VRAM is dominated by the activation memory for 161 frames at 1216×704, not the file size.
Pipeline components
| Component | Size |
|---|---|
| T5-XXL text encoder offloaded | 2.9 GB |
Video VAEs are larger than image VAEs because they decode a temporal stack of frames.
Run it
LTX-Video 13B runs in ComfyUI or Diffusers. Generating more frames or higher resolution raises peak VRAM sharply; the fp8 figure is for the default 161-frame clip.
Which devices can run LTX-Video 13B?
Apple Silicon Macs
- Apple M1 (8GB) No
- Apple M2 (16GB) No
- Apple M4 (16GB) No
- Apple M5 (16GB) No
- Apple M3 Pro (18GB) No
- Apple M4 (24GB) No
- Apple M4 Pro (24GB) No
- Apple M5 (32GB) Tight
- Apple M4 Pro (48GB) Yes
- Apple M5 Pro (48GB) Yes
- Apple M4 Max (64GB) Yes
- Apple M4 Max (128GB) Yes
- Apple M5 Max (128GB) Yes
- Apple M3 Ultra (256GB) Yes
RAM-only laptops
No mainstream local runtime for a 13B video model on RAM-only laptops yet.
iPhone & iPad
No mainstream local runtime for a 13B video model on iPhone & iPad yet.
Android
No mainstream local runtime for a 13B video model on Android yet.
NVIDIA GPUs
AMD GPUs
FAQ
How much VRAM does LTX-Video 13B need?
At fp8 the realistic peak is ~20 GB, versus ~38 GB with every component resident. With aggressive CPU offload it drops to ~12 GB, much slower.
Why is peak VRAM lower than the sum of the files?
The text encoder is run once to encode your prompt, then offloaded to CPU before the frames are generated, so it is not resident at the memory peak.
Can I use LTX-Video 13B commercially?
Yes. LTX-Video 13B is licensed LTX-Video Open Weights (OpenRAIL-M), which permits commercial use.
The 13B LTX-Video tier with a two-stage low-res-then-upscale pipeline. Backbone bf16 is 28.6GB; the fp8 backbone (15.7GB) plus the upscaler and activations peaks around ~20GB at 1216x704 (third-party measured, synthesis). bf16 needs ~38GB+ (A6000/A100). OpenRAIL-M, commercial OK. Sources: Lightricks card, 13B distilled card, diffusers LTX docs.
Sources
VRAM is a sourced peak-usage anchor at fp8 (composed from component sizes, not a single measurement) for the default clip length, validated 2026-06-15. See methodology.