tensorblock/BioLlama-Ko-8B-GGUF

Quantization vs iRASC/BioLlama-Ko-8B. tensorblock/BioLlama-Ko-8B-GGUF is a GGUF quantization (Q3_K_M) of the same weights: 65 tensors match exactly and 226 within quantization error.

Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/65, MLP 0/96, Attention 0/128

On the Hub · Downloads on Model Pulse