LTX models

5 LTX models from Lightricks on Hugging Face, from 1.9B to 19.0B parameters, published by Lightricks in F32 and BF16. The smallest official model, LTX-Video-0.9.5, needs about 4.3 GB of VRAM at its published precision; the cheapest live fit is RTX 3070 at $0.088/hr.

Pick a size

One row per official LTX size: the VRAM it needs at each precision, the cheapest GPU that holds it today, and the KV cache for a 32K-token context.

ModelParametersNative VRAMFP8 VRAMINT4 VRAMLive GPU fit (native)Est. $/hrKV cache at 32K
LTX-Video1.9B8.6 GB2.1 GB1.1 GBV100$0.110/hrnot published for this architecture
LTX-218.9B42.2 GB21.1 GB10.5 GBRTX A6000$0.363/hrnot published for this architecture
LTX-2.5-Diffusers19.0B42.4 GB21.2 GB10.6 GBRTX A6000$0.363/hrnot published for this architecture

VRAM is weights times a flat 1.2 overhead; the KV cache is a separate per-model figure at 16-bit, shown where the architecture is published. See the methodology.

Official models (4)

ModelParametersPublished asVRAM neededLive GPU fitEst. $/hr
LTX-Video1.9BF328.6 GBV100$0.110/hr
LTX-Video-0.9.51.9BBF164.3 GBRTX 3070$0.088/hr
LTX-218.9BBF1642.2 GBRTX A6000$0.363/hr
LTX-2.5-Diffusers19.0BBF1642.4 GBRTX A6000$0.363/hr

Fine-tunes and community models (1)

ModelParametersPublished asVRAM neededLive GPU fitEst. $/hr
LTX-2.3-Diffusers19.0BBF1642.4 GBRTX A6000$0.363/hr

VRAM is for the precision the model is published in: the weights times a flat 1.2 overhead, with the KV cache not included. See the methodology. The fit shown is the lowest-priced single GPU type that holds the model at that precision, or the lowest-priced multi-GPU set (up to 8) when none does.

Start ComfyUI on a rented GPU.

© 2026 Aquanode. All rights reserved.

All trademarks, logos and brand names are the property of their respective owners.