mradermacher/ANITA-NEXT-24B-Magistral-2506-VISION-ITA-GGUF
Quantization (fewer layers) vs m-polignano/ANITA-NEXT-24B-Magistral-2506-VISION-ITA. mradermacher/ANITA-NEXT-24B-Magistral-2506-VISION-ITA-GGUF matches part of m-polignano/ANITA-NEXT-24B-Magistral-2506-VISION-ITA (363 of its 585 tensors; the rest of m-polignano/ANITA-NEXT-24B-Magistral-2506-VISION-ITA has no counterpart). On the shared part: mradermacher/ANITA-NEXT-24B-Magistral-2506-VISION-ITA-GGUF is a GGUF quantization (Q8_0) of the same weights: 81 tensors match exactly and 282 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/81, MLP 0/120, Attention 0/160, lm_head 0/1