FadedRedStar/Anubis-Mini-8B-v1-heretic-imatrix-GGUF

Quantization vs coder3101/Anubis-Mini-8B-v1-heretic. FadedRedStar/Anubis-Mini-8B-v1-heretic-imatrix-GGUF is a GGUF quantization (Q5_K/Q6_K) 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