mradermacher/Huihui-GLM-4.7-Flash-abliterated-57B-GGUF

Quantization vs win10/Huihui-GLM-4.7-Flash-abliterated-57B. mradermacher/Huihui-GLM-4.7-Flash-abliterated-57B-GGUF is a GGUF quantization (Q8_0) of the same weights: 315 tensors match exactly and 443 within quantization error.

Tensors changed: Embeddings 0/1, Norms 0/253, MLP 0/251, Attention 0/252, lm_head 0/1

On the Hub · Downloads on Model Pulse