mradermacher/Apriel-1.6-15b-Thinker-Magic_beta-decensored-i1-GGUF
Quantization (fewer layers) vs MagicalAlchemist/Apriel-1.6-15b-Thinker-Magic_beta-decensored. mradermacher/Apriel-1.6-15b-Thinker-Magic_beta-decensored-i1-GGUF matches part of MagicalAlchemist/Apriel-1.6-15b-Thinker-Magic_beta-decensored (435 of its 657 tensors; the rest of MagicalAlchemist/Apriel-1.6-15b-Thinker-Magic_beta-decensored has no counterpart). On the shared part: mradermacher/Apriel-1.6-15b-Thinker-Magic_beta-decensored-i1-GGUF is a GGUF quantization (Q6_K) of the same weights: 97 tensors match exactly and 338 within quantization error.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/97, MLP 0/144, Attention 0/192