mradermacher/chatty-djinn-14B-GGUF
Quantization vs mayacinka/chatty-djinn-14B. mradermacher/chatty-djinn-14B-GGUF is a GGUF quantization (Q8_0) of the same weights: 123 tensors match exactly and 429 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/123, MLP 0/183, Attention 0/244, lm_head 0/1