Ltx GGUF models
163 GGUF models in the Ltx family, quantized by 111 uploaders. Sizes run from 1.16B to 22.2B parameters. The longest trained context is 256K tokens.
About the Ltx GGUF models
Ltx is represented on ggufmodels.com by 163 GGUF models, quantized by 111 uploaders on Hugging Face. The most downloaded are LTX 2, LTX 2.3 and LTX 2.5. Parameter counts run from 1.16B to 22.2B, and the longest trained context window is 256K tokens.
A Q4_K_M file of a Ltx model is between 1.1 to 17.8 GB, which is the quant most people start with. Most files come from vantagewithai (8), chfm (5) and Abiray (5). The quants you will meet most often are Q8_0 (128), Q4_K_M (108), Q6_K (98) and Q5_K_M (83), where the number is how many models offer that quant.
Frequently asked questions
Which Ltx GGUF should I download?
The most downloaded Ltx GGUF here is LTX 2. Pick the size that fits your GPU first, then choose a quant: Q4_K_M is the usual starting point, and Q5_K_M or Q6_K give more quality if you have memory to spare. The VRAM pages below list what fits each GPU.
How much VRAM does a Ltx model need?
Q4_K_M files of Ltx models on this site range from 1.1 to 17.8 GB. Add the KV cache for your context length and about 0.5 GB for the runtime, which usually means 1.5 to 3 GB on top of the file at an 8K context.
Where do Ltx GGUF files come from?
The most common quantizers here are vantagewithai, chfm and Abiray. They convert the original model and publish quantized files on Hugging Face. ggufmodels.com does not host files; every download button opens Hugging Face.