noctrex/DeepSeek-MoE-16B-Chat-MXFP4_MOE-GGUF

Quantization vs deepseek-ai/deepseek-moe-16b-chat. noctrex/DeepSeek-MoE-16B-Chat-MXFP4_MOE-GGUF is a GGUF quantization (MXFP4/Q8_0) 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