mradermacher/Mixtral-GQA-400m-v2-i1-GGUF
Quantization vs BEE-spoke-data/Mixtral-GQA-400m-v2. mradermacher/Mixtral-GQA-400m-v2-i1-GGUF is a GGUF quantization (Q6_K) of the same weights: 19 tensors match exactly and 26 within quantization error.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/13, other 0/6, Attention 0/24