mradermacher/Qwen3.8-20B-Minitron-GGUF
Quantization vs exnivo/Qwen3.8-20B-Minitron. mradermacher/Qwen3.8-20B-Minitron-GGUF is a GGUF quantization (Q8_0) of the same weights: 111 tensors match exactly and 178 within quantization error.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/111, MLP 0/132, Attention 0/44