magiccodingman/Apriel-1.5-15b-Thinker-unsloth-MagicQuant-Hybrid-GGUF
Quantization (fewer layers) vs unsloth/Apriel-1.5-15b-Thinker. magiccodingman/Apriel-1.5-15b-Thinker-unsloth-MagicQuant-Hybrid-GGUF matches part of unsloth/Apriel-1.5-15b-Thinker (435 of its 657 tensors; the rest of unsloth/Apriel-1.5-15b-Thinker has no counterpart). On the shared part: magiccodingman/Apriel-1.5-15b-Thinker-unsloth-MagicQuant-Hybrid-GGUF is a GGUF quantization (IQ4_NL/MXFP4) 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