Astralyra/glm-4-9b-chat-hf-Q4_K_M-GGUF

Quantization vs zai-org/glm-4-9b-chat-hf. Astralyra/glm-4-9b-chat-hf-Q4_K_M-GGUF is a GGUF quantization (Q4_K_M) of the same weights: 201 tensors match exactly and 242 within quantization error.

Tensors changed: Embeddings 0/1, Norms 0/81, MLP 0/80, Attention 0/280, lm_head 0/1

On the Hub · Downloads on Model Pulse