jakeatx/ATX-Swift-1.5-Qwen3.8-27B-Uncensored-2.3bpw-MTP-GGUF
Not comparable yet vs d0xin/Swift-1.5-Qwen3.8-27B-Uncensored-BF16. Not verifiable yet: the GGUF's tensors don't map onto the other model's names (483 of 1199/1253 match), usually an architecture llama.cpp's name map doesn't cover yet.