Nubinu/Gemma4-E4B-MiniFantasy-V1-GGUF

Same weights, converted (fewer layers) vs Nubinu/Gemma4-E4B-MiniFantasy-V1. Nubinu/Gemma4-E4B-MiniFantasy-V1-GGUF matches part of Nubinu/Gemma4-E4B-MiniFantasy-V1 (677 of its 2130 tensors; the rest of Nubinu/Gemma4-E4B-MiniFantasy-V1 has no counterpart). On the shared part: Same weights stored in another dtype (F16 → F16/F32), plus 43 new tensors.

Tensors changed: Embeddings 0/2, Norms 0/296, MLP 0/126, other 0/85, Attention 0/168

On the Hub · Downloads on Model Pulse