ubergarm/Kimi-Dev-72B-GGUF
Quantization vs moonshotai/Kimi-Dev-72B. ubergarm/Kimi-Dev-72B-GGUF is a GGUF quantization (IQ3_K) of the same weights: 401 tensors match exactly and 82 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/161, MLP 0/80, Attention 0/240, lm_head 0/1