LTX2.3 checkpoints needs about 20.4 GB of memory at Q6_K (a 17.8 GB file) with an 8K context window, so it fits on a 24 GB GPU.
LTX2.3 checkpoints is a 21B-parameter Ltx model in GGUF format, quantized by lopho. The repository has 1 quant file, from 17.8 GB (Q6_K) to 17.8 GB (Q6_K).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q6_K | 17.8 GB | 20.4 GB | Too big | Get file → |
What GPU do you need for LTX2.3 checkpoints?
These figures add the file size, an fp16 KV cache at an 8K context window and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: no quant fits at an 8K context.
- 6 GB VRAM: no quant fits at an 8K context.
- 8 GB VRAM: no quant fits at an 8K context.
- 12 GB VRAM: no quant fits at an 8K context.
- 16 GB VRAM: no quant fits at an 8K context.
- 24 GB VRAM: the best quant that fits is Q6_K (17.8 GB file, about 20.4 GB in use).
Which LTX2.3 checkpoints quant should you choose?
Q6_K (17.8 GB) is the middle option in this repository. Very close to the original quality for most uses, at a clearly larger size than 4-bit.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about LTX2.3 checkpoints
How much VRAM does LTX2.3 checkpoints need?
About 20.4 GB at Q6_K with an 8K context window. That is the 17.8 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run LTX2.3 checkpoints on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 20.4 GB, so you would need a larger GPU or CPU offloading.
What is the file size of LTX2.3 checkpoints GGUF?
It depends on the quant: Q6_K is 17.8 GB.
Where can I download LTX2.3 checkpoints GGUF?
The files are on Hugging Face in the lopho/LTX2.3_checkpoints repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.