mradermacher/Lux-V2-Pro-GGUF
Quantization (fewer layers) vs PoSTMEDIA/Lux-V2-Pro. mradermacher/Lux-V2-Pro-GGUF matches part of PoSTMEDIA/Lux-V2-Pro (772 of its 1188 tensors; the rest of PoSTMEDIA/Lux-V2-Pro has no counterpart). On the shared part: mradermacher/Lux-V2-Pro-GGUF is a GGUF quantization (Q8_0) of the same weights: 361 tensors match exactly and 411 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/361, MLP 0/180, Attention 0/230