mradermacher/Springer1.0-32B-Qwen2.5-Reasoning-GGUF
Quantization vs marcuscedricridia/Springer1.0-32B-Qwen2.5-Reasoning. mradermacher/Springer1.0-32B-Qwen2.5-Reasoning-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