mradermacher/Mag-Mell-R1-21B-i1-GGUF
Quantization vs Frowning/Mag-Mell-R1-21B. mradermacher/Mag-Mell-R1-21B-i1-GGUF is a GGUF quantization (Q6_K) of the same weights: 141 tensors match exactly and 492 within quantization error.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/141, MLP 0/210, Attention 0/280