mradermacher/Haruhi-Zero-1_8B-0_4-i1-GGUF
Quantization vs silk-road/Haruhi-Zero-1_8B-0_4. mradermacher/Haruhi-Zero-1_8B-0_4-i1-GGUF is a GGUF quantization (Q6_K) of the same weights: 121 tensors match exactly and 170 within quantization error.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/49, MLP 0/72, Attention 0/168