toandev/Spark-X2.5-4B-Uncensored-GGUF

Quantization vs toandev/Spark-X2.5-4B-Uncensored. toandev/Spark-X2.5-4B-Uncensored-GGUF is a GGUF quantization (Q8_0) of the same weights: 73 tensors match exactly and 182 within quantization error.

Tensors changed: Embeddings 0/1, Norms 0/73, MLP 0/108, Attention 0/72, lm_head 0/1

On the Hub · Downloads on Model Pulse