LTX 2.3
Q4 GGUF download: unsloth/LTX-2.3-GGUF - 14.19 GB on disk, read 2026-09-27. VRAM figures above are estimates; this is the actual file size.
Will it run on your hardware?
Pick your GPU memory - see which quantizations fit, and the cheapest card for the rest
Need an exact figure for your context length? Use the VRAM calculator.
Run it locally
Copy-paste - running in under a minute
vllm serve Lightricks/LTX-2.3New to this? Start with Ollama · serve to many users with vLLM.
Deep dive
Notes, sources, and the full write-up
LTX 2.3
LTX 2.3 by Lightricks is the most popular open image-to-video model with 2.29 million monthly downloads. It animates still images into smooth video clips and also supports text-to-video generation.
Key features
- 2.29M monthly downloads - most popular I2V model
- Image-to-video - animate any still image
- Text-to-video - also supports T2V
- 21B parameters - DiT-based architecture
- GGUF support - quantized for lower VRAM
- ComfyUI - node-based workflow support
- Community ecosystem - 244K+ LoRAs and finetunes
How to run
from diffusers import LTXPipeline
import torch
pipe = LTXPipeline.from_pretrained(
"Lightricks/LTX-2.3",
torch_dtype=torch.bfloat16
).to("cuda")
# Image-to-video
from PIL import Image
image = Image.open("input.jpg")
video = pipe(image, num_frames=49).frames[0]VRAM
| Quant | VRAM |
|---|---|
| BF16 | ~42 GB |
| FP8 | ~24 GB |
| GGUF Q8 | ~22 GB |
When to use
- Social media - animate photos for reels
- Marketing - product video from stills
- Creative - bring artwork to life
- Storyboarding - quick motion tests
From the community
What users are saying
“Tried on workflows like FL2V and ic-lora (controlNet). After the first generation step, the last frame corresponds to the last frame, the movements correspond to the original video. After the second step, the final frame roughly corresponds to the prompt rather than the final frame.”
“64GB Ram, RTX 5090 Dev FP8, 8 step, 1280X720 82 sec for 481 frames. Going less frames only saves 2-5 secs since most the time is loading the model. 564sec for 961 frames”
“root=/xxx/xx/ outputv1.mp4: https://cdn-uploads.huggingface.co/production/uploads/671a027d0bb4fe583845637b/HJ12nnsLyFDEFP5ZzxO4c.mp4 outputv2.mp4: https://cdn-uploads.huggingface.co/production/uploads/671a027d0bb4fe583845637b/-icOFpilxjROjYodW6DD.mp4”
Frequently asked
Quick answers to common questions
How much VRAM does LTX 2.3 need?
LTX 2.3 with 21B parameters needs significant VRAM depending on quantization. Use our VRAM calculator for an exact estimate.
Is LTX 2.3 better than other LTX models?
LTX 2.3 has 21B parameters with 8,192 context - a strong choice for image-to-video, video-generation.
What license is LTX 2.3 under?
LTX 2.3 is released under the Other license, making it suitable for most commercial and personal projects.
What hardware runs LTX 2.3 well?
With 21B parameters, LTX 2.3 requires adequate VRAM. High-end GPUs like the RTX 4090 (24GB), RTX 5090 (32GB), or Mac Studio with unified memory are good options. Check our hardware directory for specific recommendations.
What is the best quantization for LTX 2.3?
Q4_K_M is the recommended sweet spot - ~98% of FP16 quality at ~27% of the size. Step up to Q5_K_M or Q8_0 only if you have spare VRAM. Use our VRAM calculator to compare.
What models compete with LTX 2.3?
LTX 2.3 competes with other models in its class. Browse our model directory for comparisons, benchmarks, and community reviews to find the best fit.
Compare & pair with
Similar models and recommended hardware
Nearby options
Similar models and compatible hardware by spec