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