mradermacher/Gemma4-LitLit-e2b-GGUF

Same weights, converted (fewer layers) vs theprint/Gemma4-LitLit-e2b. mradermacher/Gemma4-LitLit-e2b-GGUF matches part of theprint/Gemma4-LitLit-e2b (565 of its 2011 tensors; the rest of theprint/Gemma4-LitLit-e2b has no counterpart). On the shared part: Same weights stored in another dtype (BF16 → F16/BF16), 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