mradermacher/b1ade-1b-bf16-i1-GGUF
Quantization vs w601sxs/b1ade-1b-bf16. mradermacher/b1ade-1b-bf16-i1-GGUF is a GGUF quantization (IQ1_M) of the same weights: 114 tensors match exactly and 50 within quantization error.
Tensors changed: Embeddings 0/2, Norms 0/66, Attention 0/32, MLP 0/64