mradermacher/Mistral-Small-3.2-46B-The-Brilliant-Raconteur-II-Instruct-2506-GGUF
Quantization vs DavidAU/Mistral-Small-3.2-46B-The-Brilliant-Raconteur-II-Instruct-2506. mradermacher/Mistral-Small-3.2-46B-The-Brilliant-Raconteur-II-Instruct-2506-GGUF is a GGUF quantization (Q8_0) of the same weights: 159 tensors match exactly and 555 within quantization error.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/159, MLP 0/237, Attention 0/316