Skip to content
localmodel.run

video model · ltx-video · Windows

LX Can I run LTX-Video 13B on Nvidia GeForce RTX 4090 (24GB)?

Compatibility verdict VRAM check
Yes, it runsfast on this GPU

Yes. LTX-Video 13B runs on Nvidia GeForce RTX 4090 (24GB) at fp8 (~20 GB of ~23 GB usable).

Needs ~20 GB Device usable ~23 GB

Runs at fp8 using ~20 GB of ~23 GB usable.

Peak VRAM
~20 GB
Usable on device
~23 GB
Device memory
24 GB
Quant
fp8

How to run it

Use ComfyUI or Diffusers at fp8. 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.

Model ltx-video
Type
video (DIT)
Parameters
13B
Peak VRAM
~20 GB at fp8
Resolution
1216×704
License
LTX-Video Open Weights (OpenRAIL-M)
Full LTX-Video 13B requirements →
Device Windows
Memory
24 GB vram
Usable for weights
~23 GB
Best runtime
vLLM (Linux) / Ollama (CUDA)
Best models for Nvidia GeForce RTX 4090 (24GB) →

You could also run

Run LTX-Video 13B on other hardware

FAQ

Can Nvidia GeForce RTX 4090 (24GB) run LTX-Video 13B?

Yes. LTX-Video 13B runs on Nvidia GeForce RTX 4090 (24GB) at fp8 (~20 GB of ~23 GB usable).

How much VRAM does LTX-Video 13B need?

Nvidia GeForce RTX 4090 (24GB) has room to spare. At fp8 the realistic peak is ~20 GB of VRAM, versus ~38 GB with every component kept resident (no offload). With aggressive CPU offload it drops to ~12 GB, much slower.

What do I use to run LTX-Video 13B locally?

LTX-Video 13B 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.