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