mradermacher/GLM-4-32B-Base-32K-GGUF

Quantization vs arcee-ai/GLM-4-32B-Base-32K. mradermacher/GLM-4-32B-Base-32K-GGUF is a GGUF quantization (Q8_0) of the same weights: 245 tensors match exactly and 368 within quantization error.

Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/245, MLP 0/122, Attention 0/244

On the Hub · Downloads on Model Pulse