mradermacher/Kimi-K2.5-BF16-Pruned-20B-i1-GGUF
Quantization vs ubicloud/Kimi-K2.5-BF16-Pruned-20B. mradermacher/Kimi-K2.5-BF16-Pruned-20B-i1-GGUF is a GGUF quantization (IQ1_M) of the same weights: 10 tensors match exactly and 16 within quantization error.
Tensors changed: Norms 0/9, MLP 0/7, Attention 0/8, lm_head 0/1, Embeddings 0/1