mradermacher/ScreenHighlighterRL-2B-i1-GGUF
Quantization (fewer layers) vs mustafaah/ScreenHighlighterRL-2B. mradermacher/ScreenHighlighterRL-2B-i1-GGUF matches part of mustafaah/ScreenHighlighterRL-2B (310 of its 625 tensors; the rest of mustafaah/ScreenHighlighterRL-2B has no counterpart). On the shared part: mradermacher/ScreenHighlighterRL-2B-i1-GGUF is a GGUF quantization (Q6_K) of the same weights: 113 tensors match exactly and 197 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/113, MLP 0/84, Attention 0/112