Lightricks · First MLX build 12 Aug 2026
LTX-2.5
MLX
Image ltx-2-community-license-agreement Trending
A text to video model from Lightricks, with 3 MLX builds at 8-bit.
- Parameters
- — Not published
- Quantisation
- 8-bit ltx-2.5-mlx-q8
- Memory needed
- — GB Estimate, unified memory
- Download
- — Weights, estimated
- Downloads
- 613 This build, last 30 days
- Task
- Text to video Image
- MLX builds
- 3 On mlx-community
- Devices
- Mac Apple silicon
Memory
Hugging Face does not list a weights size for this build, so there is no memory estimate.
Estimated from the size of the weights, plus a fifth for context and working memory and 2 GB for macOS and your apps. Long contexts need more.
Run it
Terminal · Hugging Face CLI$ pip install -U huggingface_hub
$ hf download mlx-community/ltx-2.5-mlx-q8MLX builds
3 on mlx-community| ltx-2.5-mlx-q8 | 8-bit | — | — | 613 |
|---|---|---|---|---|
| ltx-2.5-mlx | Unstated | — | — | 536 |
| ltx-2.5-mlx-ditq8 | Unstated | — | — | 0 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.