mradermacher/DwQ-R1-32B-v0.1-GGUF
Quantization vs DataSoul/DwQ-R1-32B-v0.1. mradermacher/DwQ-R1-32B-v0.1-GGUF is a GGUF quantization (Q8_0) of the same weights: 321 tensors match exactly and 450 within quantization error.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/129, MLP 0/192, Attention 0/448