mradermacher/whale-v3-base-merged-GGUF
Quantization vs theblackcat102/whale-v3-base-merged. mradermacher/whale-v3-base-merged-GGUF is a GGUF quantization (Q8_0) of the same weights: 245 tensors match exactly and 429 within quantization error.
Tensors changed: MLP 0/183, Attention 0/244, Embeddings 0/1, Norms 0/245, lm_head 0/1