What GPU do I need to run Lightricks/LTX-Video?
1.9B parameters, published in F32. View on Hugging Face
LTX-Video is published by Lightricks on Hugging Face, with 504,409 downloads and 2,286 likes to date. It's a unlisted-architecture model built for image-to-video, published natively in F32.
VRAM required & cheapest live GPU fit
Required VRAM = weight size at each precision, plus a fixed overhead for activation memory and allocator fragmentation. Diffusion and video models carry no KV-cache. The real driver of extra memory is output resolution and frame count, which this flat overhead does not model. Full formula and assumptions: methodology.
| Precision | Weight size | Required VRAM | Cheapest live fit | GPUs needed | Est. $/hr (full fit) |
|---|---|---|---|---|---|
| FP32 | 7.2 GB | 8.6 GB | V100 | 1 | $0.110/hr |
| FP8 (quantized) | 1.8 GB | 2.1 GB | RTX 5060 Ti | 1 | $0.180/hr |
| INT4 (quantized) | 0.9 GB | 1.1 GB | RTX 3070 | 1 | $0.088/hr |
A GPU is only matched to a row if its hardware supports that precision, and the primary recommendation is always a single-GPU fit when one exists.
INT4 requires a quantized checkpoint actually published for this model, check its Hugging Face page before relying on this row.
Cheapest way to run LTX-Video at its published (F32) precision: 1× V100, at $0.110/hr per GPU ($0.110/hr total). Quantizing to FP8 or INT4 (rows above) can cost less, but requires a compatible quantized checkpoint to exist for this model.
LTX-Video: common questions
Does LTX-Video fit on a 12 GB GPU?
Yes. At FP32 it needs 8.6 GB of VRAM, so a 12 GB card holds it with 3.4 GB to spare. An 8 GB card is not enough for it at FP32.
Can LTX-Video run in 16-bit instead of FP32?
Yes. Its published weights are FP32, 7.2 GB, or 8.6 GB once inference overhead is added. Loading the same weights in 16 bits halves that to 3.6 GB, or 4.3 GB with overhead. That moves it onto a 6 GB card instead of a 12 GB one. How much accuracy the cast costs is model-specific and is not measured here.
What is the least VRAM LTX-Video can run in?
1.1 GB, at INT4 (quantized), which fits a 6 GB card, against 8.6 GB at FP32. That row assumes an INT4 checkpoint has actually been published for this model, so check its Hugging Face page before planning around it.
Does quantizing LTX-Video lower the GPU bill?
Yes. At FP32 the cheapest live fit is one V100 at $0.110/hr. At INT4 (quantized) it drops to one RTX 3070 at $0.088/hr, provided a quantized checkpoint exists for it.
Weight-to-VRAM math, the fit rules, and how live prices are normalized: full methodology.
More LTX models
- LTX-Video-0.9.5 (1.9B, BF16)
- LTX-2 (18.9B, BF16)
- LTX-2.5-Diffusers (19.0B, BF16)
- LTX-2.3-Diffusers (19.0B, BF16)
Alternatives at this size
Other models for image-to-video within about a third of LTX-Video's 1.9B parameters, from other model lines.
- stable-video-diffusion-img2vid-xt (1.5B, F32)
- Wan2.1-VACE-1.3B-diffusers (2.2B, F32)
More on LTX-Video
Fits on a 12 GB GPU at FP32: every model that fits in 12 GB.
Fits on an 8 GB GPU at FP8: every model that fits in 8 GB.
Best video generation models: how LTX-Video ranks against the rest.
Related reading: V100 pricing and specs, Fast diffusion inference on GPU VMs, and What AI inference is.
ComfyUI on our compute
Rent a GPU with ComfyUI already installed. Your custom nodes and models are there next time.
$29 a month, or pay as you go