mradermacher/Qwenseek-3.8-27B-CyberLite-BF16-GGUF
Quantization vs trjxter/Qwenseek-3.8-27B-CyberLite-BF16. mradermacher/Qwenseek-3.8-27B-CyberLite-BF16-GGUF is a GGUF quantization (IQ4_XS) of the same weights: 161 tensors match exactly and 258 within quantization error.
Tensors changed: lm_head 0/1, Norms 0/161, Embeddings 0/1, MLP 0/192, Attention 0/64