mradermacher/ChindaMT-0.8B-i1-GGUF
Quantization vs iapp/ChindaMT-0.8B. mradermacher/ChindaMT-0.8B-i1-GGUF is a GGUF quantization (Q6_K) of the same weights: 61 tensors match exactly and 98 within quantization error.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/61, MLP 0/72, Attention 0/24