kingjones777/Qwen3.8-27B-Uncensored-ROCmFP4-STRIX-MTP-GGUF
Same weights, converted vs Qwen/Qwen3.8-27B. Same weights stored in another dtype (BF16 → T103/T102), plus 48 new tensors.
Tensors changed: Norms 0/161
Same weights, converted vs Qwen/Qwen3.8-27B. Same weights stored in another dtype (BF16 → T103/T102), plus 48 new tensors.
Tensors changed: Norms 0/161