jakeatx/ATX-Swift-Qwen3.8-27B-Uncensored-IQ4_XS-M-GGUF
Quantization vs d0xin/Swift-Qwen3.8-27B-Uncensored-BF16. jakeatx/ATX-Swift-Qwen3.8-27B-Uncensored-IQ4_XS-M-GGUF is a GGUF quantization (IQ4_XS/Q5_0) 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