LTX-2.3-22B - GGUF

GGUF quantizations of Lightricks/LTX-2.3.

Files

file size
ltx-2.3-22b-dev-BF16.gguf 39.15 GB
ltx-2.3-22b-dev-Q4_K_M.gguf 13.22 GB
ltx-2.3-22b-dev-Q8_0.gguf 21.19 GB

Usage

These GGUF files are quantized versions of the LTX-2.3 22B Distilled 1.1 model.

Available quantizations:

  • BF16 - highest precision / largest file
  • Q8_0 - near-lossless quality
  • Q4_K_M - significantly smaller with good quality

Q8_0 is generally the best choice when you have enough VRAM/RAM.

License

Licensing follows the original model: Lightricks/LTX-2.3.

Downloads last month
-
GGUF
Model size
21B params
Architecture
ltxv
Hardware compatibility
Log In to add your hardware

4-bit

8-bit

16-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for TachyHealthResearch/ltx-2.3-22b-gguf

Quantized
(61)
this model