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.
| Model | Parameters | Native VRAM | FP8 VRAM | INT4 VRAM | Live GPU fit (native) | Est. $/hr | KV cache at 32K |
|---|---|---|---|---|---|---|---|
| LTX-Video | 1.9B | 8.6 GB | 2.1 GB | 1.1 GB | V100 | $0.110/hr | not published for this architecture |
| LTX-2 | 18.9B | 42.2 GB | 21.1 GB | 10.5 GB | RTX A6000 | $0.363/hr | not published for this architecture |
| LTX-2.5-Diffusers | 19.0B | 42.4 GB | 21.2 GB | 10.6 GB | RTX A6000 | $0.363/hr | not 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)
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| LTX-Video | 1.9B | F32 | 8.6 GB | V100 | $0.110/hr |
| LTX-Video-0.9.5 | 1.9B | BF16 | 4.3 GB | RTX 3070 | $0.088/hr |
| LTX-2 | 18.9B | BF16 | 42.2 GB | RTX A6000 | $0.363/hr |
| LTX-2.5-Diffusers | 19.0B | BF16 | 42.4 GB | RTX A6000 | $0.363/hr |
Fine-tunes and community models (1)
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| LTX-2.3-Diffusers | 19.0B | BF16 | 42.4 GB | RTX 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.