LTX-Video (2B Realtime)
Real-time 2B spatial-temporal video DiT capable of generating 24fps high-resolution video in under 15 seconds on consumer GPUs under Apache 2.0.
The brutal truth
Generates 24fps video in seconds instead of minutes. On an 8GB card, it feels like magic compared to the painful wait times of older video models.
Files and Versions
Direct inspected tree artifacts from Hugging Face. Verified filenames, exact byte sizes, model weight shards, and configuration definitions.
Files and versions are hosted on Hugging Face. You can view all branches, commits, model weights, and tokenizer artifacts directly.
Inspect Lightricks/LTX-Video /tree/main ↗Inspect /tree/main Repository ↗Decision matrix
✓ RUN / USE THIS IF…
- •You have an 8GB or 12GB GPU
- •You want near-realtime video prototyping in ComfyUI
- •Your 24GB GPU comfortably fits the model weights (~9GB VRAM) with dedicated headroom for inference.
- •You require 100% offline data privacy with zero third-party API logging, subscriptions, or prompt retention.
✕ WALK AWAY IF…
- •You need 1080p photorealistic human faces (use Hunyuan)
- •Your GPU has less than 9GB VRAM and you cannot tolerate slow CPU/system RAM offload paging.
- •You prefer a plug-and-play web app interface and don't want to manage local model checkpoints, drivers, or runtimes.
- •You need specialized frontier reasoning that exceeds this model's parameter envelope.
True cost of ownership
About
Real-time 2B spatial-temporal video DiT capable of generating 24fps high-resolution video in under 15 seconds on consumer GPUs under Apache 2.0.
What it does
Download the weights from Hugging Face, pick a quantisation that matches your GPU, and run it locally with Ollama, llama.cpp, vLLM, or a compatible runtime. Sub-20-second realtime video generation on 8GB GPUs runs on your own hardware — no per-token bill, no third-party data handling.
Key features
Fastest video model available: generates clips in 10-20 seconds
Fits in 8GB–12GB VRAM consumer graphics cards
Apache 2.0 license
Use cases
Turn a script into a polished 15–30 second clip.
Visualise shot lists before a full production run.
Fill timeline gaps with convincing atmospheric footage.
Create stylised clips from a lyric sheet or mood board.
Quantization & Hardware Fit
VRAM Hardware Compatibility & Memory Allocation
| Quant | VRAM | Quality / Fit on 24GB | Install / Run Command (COMFYUI) | |
|---|---|---|---|---|
| BF16● ACTIVE | 9 GB | Standard · ✓ Fits (15GB spare) | comfy model download --url https://huggingface.co/Lightricks/LTX-Video --relative-path models/diffusion_models | |
| FP8 | 6 GB | Standard · ✓ Fits (18GB spare) | comfy model download --url https://huggingface.co/Lightricks/LTX-Video --relative-path models/diffusion_models |
Buyer doubts, cleared
Can I actually run LTX-Video (2B Realtime) on my 24GB GPU?
What's the fine print on the license?
Does the Realtime Text-to-video (2B DiT) actually hold up in practice?
User reviews
Solid for sub-20-second realtime video generation on 8gb gpus. The learning curve is real but the payoff is there. Start with the smaller build first.
Clean interface, consistent results once you land on a prompt you like. Wish there were more export presets for client handoffs.
The BF16 build is the sweet spot. Anything larger needs serious hardware for marginal quality gains.
LTX-Video (2B Realtime) handled our batch jobs without surprises. The API is well documented and the rate limits are reasonable.
