mradermacher/Cerebras-OPT-Fusion-i1-GGUF
Quantization vs MatteoKhan/Cerebras-OPT-Fusion. mradermacher/Cerebras-OPT-Fusion-i1-GGUF is a GGUF quantization (Q6_K) of the same weights: 259 tensors match exactly and 1 within quantization error.
Tensors changed: Attention 0/64, Norms 0/130, MLP 0/64, Embeddings 0/2