Soulfate24/Spark-X2.5-4B-Paretrix

Not comparable yet vs XHToken/Spark-X2.5-4B. Not verifiable yet: the GGUF's tensors don't map onto the other model's names (0 of 290/432 match), usually an architecture llama.cpp's name map doesn't cover yet.

On the Hub · Downloads on Model Pulse