mradermacher/nekomata-7b-i1-GGUF

Quantization vs rinna/nekomata-7b. mradermacher/nekomata-7b-i1-GGUF is a GGUF quantization (Q6_K) of the same weights: 97 tensors match exactly and 162 within quantization error.

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

On the Hub · Downloads on Model Pulse