aclava/deepseek-moe-16b-chat-Q4_K_M-GGUF

Quantization vs deepseek-ai/deepseek-moe-16b-chat. aclava/deepseek-moe-16b-chat-Q4_K_M-GGUF is a GGUF quantization (Q4_K_M) of the same weights: 84 tensors match exactly and 198 within quantization error.

Tensors changed: Embeddings 0/1, Norms 0/57, MLP 0/111, Attention 0/112, lm_head 0/1

On the Hub · Downloads on Model Pulse