mradermacher/gemma-4-E2B-OBLITERATED-GGUF

Same weights, converted (fewer layers) vs joysikd/gemma-4-E2B-OBLITERATED. mradermacher/gemma-4-E2B-OBLITERATED-GGUF matches part of joysikd/gemma-4-E2B-OBLITERATED (505 of its 1951 tensors; the rest of joysikd/gemma-4-E2B-OBLITERATED 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