Takenoko12345678/Spark-X2.5-4B-Japanese-GGUF

Quantization vs Takenoko12345678/Spark-X2.5-4B-Japanese. Takenoko12345678/Spark-X2.5-4B-Japanese-GGUF is a GGUF quantization (Q8_0) of the same weights: 73 tensors match exactly and 181 within quantization error.

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

On the Hub · Downloads on Model Pulse