mradermacher/SJT-24B-Alpha-i1-GGUF
Quantization vs Sakalti/SJT-24B-Alpha. mradermacher/SJT-24B-Alpha-i1-GGUF is a GGUF quantization (Q6_K) of the same weights: 411 tensors match exactly and 576 within quantization error.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/165, MLP 0/246, Attention 0/574