mradermacher/M.O.G.-SEC-27B-1M-CTX-BF16-i1-GGUF
Quantization vs Blackfrost-Research/M.O.G.-SEC-27B-1M-CTX-BF16. mradermacher/M.O.G.-SEC-27B-1M-CTX-BF16-i1-GGUF is a GGUF quantization (IQ3_M) of the same weights: 161 tensors match exactly and 258 within quantization error.
Tensors changed: Norms 0/161, MLP 0/192, Attention 0/64, Embeddings 0/1, lm_head 0/1