DavidAU
/

Llama-3.2-8X3B-MOE-Dark-Champion-Instruct-uncensored-abliterated-18.4B-GGUF

Model card Files Files and versions Community

DavidAU commited on Feb 12

Commit

5322867

·

verified ·

1 Parent(s): af41df8

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -50,7 +50,7 @@ And it is fast: 50+ t/s (2 experts) on a low end 16GB card, IQ4XS.
 Double this speed for standard/mid-range video cards.
-<B>NEW: Version 2 with Brainstorm 5x infused on all 8 models, creating a 8X4B MOE is located here:</B>
 [ https://huggingface.co/DavidAU/Llama-3.2-8X4B-MOE-V2-Dark-Champion-Instruct-uncensored-abliterated-21B-GGUF ]

 Double this speed for standard/mid-range video cards.
+<B>NEW: Version 2 quanted using the newest Llamacpp version, with Brainstorm 5x infused in all 8 models (creating a 8X4B MOE), and mastered from float 32 files is located here:</B>
 [ https://huggingface.co/DavidAU/Llama-3.2-8X4B-MOE-V2-Dark-Champion-Instruct-uncensored-abliterated-21B-GGUF ]