Koshkasa/Vortex5_Phoenix-X-26B-A4B-MXFP4_MOE-GGUF

What's that?

MXFP4MOE quantization of [Vortex5/Phoenix-X-26B-A4B](https://huggingface.co/Vortex5/Phoenix-X-26B-A4B) with more aggressive compression than standard mxfp4moe. Local attention at IQ4XS, global attention at Q5K, attnoutput in global attention layers in Q6K.

imatrix generated by alexokita

Disclosure

My only contribution is compute. This is not my merge. Have fun.

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