mradermacher/OpenAster1-4k-base-i1-GGUF
Quantization vs binichallein/OpenAster1-4k-base. mradermacher/OpenAster1-4k-base-i1-GGUF is a GGUF quantization (Q6_K) of the same weights: 91 tensors match exactly and 73 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/73, MLP 0/18, Attention 0/72