
DavidAU/Qwen3-30B-A6B-16-Extreme
Text Generation
•
Updated
•
15
•
3
Qwen3s: 0.6B, 1.7B, 4B, 8B, 14B, 30B (MOE), 32B using Neo / Horror / Other imatrix datasets, exp methods, and ways to improve reasoning/output gen.
Note Non-Imatrix Q8 versions with different context lengths, with 256K twice the Qwen recommended context ... it works.
Note Non-Imatrix Q8 versions with different context lengths, with 256K twice the Qwen recommended context ... it works.
Note Experimental using an Imatrix datasets (2) from a single author to modify prose/general operation of the model. Example generations / method to test provided.