Nubinu/Gemma4-E2B-MicroFantasy-V1-GGUF

Same weights, converted (fewer layers) vs Nubinu/Gemma4-E2B-MicroFantasy-V1. Nubinu/Gemma4-E2B-MicroFantasy-V1-GGUF matches part of Nubinu/Gemma4-E2B-MicroFantasy-V1 (565 of its 2011 tensors; the rest of Nubinu/Gemma4-E2B-MicroFantasy-V1 has no counterpart). On the shared part: Same weights stored in another dtype (F16 → F16/F32), plus 36 new tensors.

Tensors changed: Embeddings 0/2, Norms 0/247, MLP 0/105, other 0/71, Attention 0/140

On the Hub · Downloads on Model Pulse