mradermacher/gemma-4-E2B-it-qat-q4_0-unquantized-GGUF

Same weights, converted (fewer layers) vs google/gemma-4-E2B-it-qat-q4_0-unquantized. mradermacher/gemma-4-E2B-it-qat-q4_0-unquantized-GGUF matches part of google/gemma-4-E2B-it-qat-q4_0-unquantized (505 of its 1951 tensors; the rest of google/gemma-4-E2B-it-qat-q4_0-unquantized 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 0/227, MLP 0/105, other 0/71, Attention 0/100

On the Hub · Downloads on Model Pulse