mradermacher/BigWeave-v28-96b-i1-GGUF
Quantization vs llmixer/BigWeave-v28-96b. mradermacher/BigWeave-v28-96b-i1-GGUF is a GGUF quantization (Q3_K_M) of the same weights: 225 tensors match exactly and 786 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/225, MLP 0/336, Attention 0/448, lm_head 0/1