mradermacher/Apriel-1.6-15b-Thinker-heretic-GGUF
Quantization (fewer layers) vs MRockatansky/Apriel-1.6-15b-Thinker-heretic. mradermacher/Apriel-1.6-15b-Thinker-heretic-GGUF matches part of MRockatansky/Apriel-1.6-15b-Thinker-heretic (435 of its 657 tensors; the rest of MRockatansky/Apriel-1.6-15b-Thinker-heretic has no counterpart). On the shared part: mradermacher/Apriel-1.6-15b-Thinker-heretic-GGUF is a GGUF quantization (Q8_0) of the same weights: 97 tensors match exactly and 338 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/97, MLP 0/144, Attention 0/192, lm_head 0/1