video model · ltx-video · Windows
LX Can I run LTX-Video 2B on Nvidia GeForce RTX 4080 (16GB)?
Yes. LTX-Video 2B runs on Nvidia GeForce RTX 4080 (16GB) at fp8 + offload (~10 GB of ~15 GB usable).
Runs at fp8 + offload using ~10 GB of ~15 GB usable.
- Peak VRAM
- ~10 GB
- Usable on device
- ~15 GB
- Device memory
- 16 GB
- Quant
- fp8 + offload
How to run it
Use ComfyUI or Diffusers at fp8 + offload. The big text encoder is loaded to encode your prompt, then offloaded before generation, which is why peak VRAM stays near the backbone size rather than the sum of every file.
- Type
- video (DIT)
- Parameters
- 2B
- Peak VRAM
- ~10 GB at fp8 + offload
- Resolution
- 1216×704
- License
- LTX-Video Open Weights (OpenRAIL-M)
- Memory
- 16 GB vram
- Usable for weights
- ~15 GB
- Best runtime
- vLLM (Linux) / Ollama (CUDA)
You could also run
Run LTX-Video 2B on other hardware
FAQ
Can Nvidia GeForce RTX 4080 (16GB) run LTX-Video 2B?
Yes. LTX-Video 2B runs on Nvidia GeForce RTX 4080 (16GB) at fp8 + offload (~10 GB of ~15 GB usable).
How much VRAM does LTX-Video 2B need?
Nvidia GeForce RTX 4080 (16GB) has room to spare. At fp8 + offload the realistic peak is ~10 GB of VRAM, versus ~12 GB with every component kept resident (no offload). With aggressive CPU offload it drops to ~6 GB, much slower.
What do I use to run LTX-Video 2B locally?
LTX-Video 2B runs in ComfyUI or Diffusers. It loads as a video diffusion checkpoint plus its text encoder and VAE, not a single chat command.
Sources
VRAM figures are sourced peak-usage anchors at the noted quant, validated 2026-06-15. See methodology.