huihui-ai/Huihui-Qwable-3.6-27b-abliterated-MTP-GGUF
Quantization vs Mia-AiLab/Qwable-3.6-27b. huihui-ai/Huihui-Qwable-3.6-27b-abliterated-MTP-GGUF is a GGUF quantization (F16/Q4_K) of the same weights: 723 tensors match exactly and 128 within quantization error.
Tensors changed: lm_head 0/1, Norms 0/209, other 0/289, Attention 0/160, MLP 0/192
2 derivatives checked
- rcmorano/Huihui-Qwable-3.6-27b-abliterated-MTP-ROCMFPX: Same weights, repacked
- coolthor/Huihui-Qwable-3.6-27b-abliterated-Q4_K_M-MTP-GGUF: Quantization