mradermacher/SJT-2.1B-i1-GGUF
Quantization vs Sakalti/SJT-2.1B. mradermacher/SJT-2.1B-i1-GGUF is a GGUF quantization (Q6_K) of the same weights: 176 tensors match exactly and 247 within quantization error.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/71, MLP 0/105, Attention 0/245