mradermacher/Gemma4-E4B-SFT-Fable5-GGUF
Same weights, converted (fewer layers) vs ermiaazarkhalili/Gemma4-E4B-SFT-Fable5. mradermacher/Gemma4-E4B-SFT-Fable5-GGUF matches part of ermiaazarkhalili/Gemma4-E4B-SFT-Fable5 (677 of its 2130 tensors; the rest of ermiaazarkhalili/Gemma4-E4B-SFT-Fable5 has no counterpart). On the shared part: Same weights stored in another dtype (BF16 → F16/BF16), plus 43 new tensors.
Tensors changed: Embeddings 0/2, Norms 0/296, MLP 0/126, other 0/85, Attention 0/168