jkim96/GLM-4-32B-0414-DASHQ-Q2-GGUF

Quantization vs zai-org/GLM-4-32B-0414. jkim96/GLM-4-32B-0414-DASHQ-Q2-GGUF is a GGUF quantization (IQ2_XS) of the same weights: 245 tensors match exactly and 368 within quantization error.

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

On the Hub · Downloads on Model Pulse