mradermacher/SJT-2.4B-i1-GGUF
Quantization vs Sakalti/SJT-2.4B. mradermacher/SJT-2.4B-i1-GGUF is a GGUF quantization (Q6_K) of the same weights: 211 tensors match exactly and 296 within quantization error.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/85, MLP 0/126, Attention 0/294