Koshkasa/Vortex5_Phoenix-X-26B-A4B-IQ4_NL-GGUF

What's that?

Mixed precision mainly IQ4NL quantization of [Vortex5/Phoenix-X-26B-A4B](https://huggingface.co/Vortex5/Phoenix-X-26B-A4B). Precision was quanted up to Q6K in 3 beginning and end layers, as well as global attn layers, resulting in 10/30 attn-related tensor groups being Q6K. IQ4NL was chosen specifically for outlier handling. In my testing, even IQ4_XS does break MoE occasionally, unless you're building it from a QAT checkpoint. Deliberately stepping away from mixed math/article/story/rp soup datasets, imatrix dataset is a random conversation 250000-token prune of Squish42/bluemoon-fandom-1-1-rp-cleaned.

Disclosure

My only contribution is compute. This is neither my merge nor my dataset. WYSIWYG. Have fun.

Model card incomplete. Tests and comparisons may be uploaded at a later date.