mradermacher/Ministral-3-14B-Nymphaea-RP-GGUF
Quantization (fewer layers) vs 0xA50C1A1/Ministral-3-14B-Nymphaea-RP. mradermacher/Ministral-3-14B-Nymphaea-RP-GGUF matches part of 0xA50C1A1/Ministral-3-14B-Nymphaea-RP (363 of its 585 tensors; the rest of 0xA50C1A1/Ministral-3-14B-Nymphaea-RP has no counterpart). On the shared part: mradermacher/Ministral-3-14B-Nymphaea-RP-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