mradermacher/GLM-4.7-Flash-49B-GGUF

Quantization vs win10/GLM-4.7-Flash-49B. mradermacher/GLM-4.7-Flash-49B-GGUF is a GGUF quantization (Q8_0) of the same weights: 375 tensors match exactly and 527 within quantization error.

Tensors changed: Embeddings 0/1, Norms 0/301, MLP 0/299, Attention 0/300, lm_head 0/1

On the Hub · Downloads on Model Pulse