mradermacher/Huihui-GLM-4.7-Flash-abliterated-60B_DEPTHONLY-GGUF

Quantization vs win10/Huihui-GLM-4.7-Flash-abliterated-60B_DEPTHONLY. mradermacher/Huihui-GLM-4.7-Flash-abliterated-60B_DEPTHONLY-GGUF is a GGUF quantization (Q8_0) of the same weights: 465 tensors match exactly and 653 within quantization error.

Tensors changed: Embeddings 0/1, Norms 0/373, MLP 0/371, Attention 0/372, lm_head 0/1

On the Hub · Downloads on Model Pulse