mradermacher/TurboGemma4E2B-GGUF

Same weights, converted (fewer layers) vs DuoNeural/TurboGemma4E2B. mradermacher/TurboGemma4E2B-GGUF matches part of DuoNeural/TurboGemma4E2B (565 of its 1883 tensors; the rest of DuoNeural/TurboGemma4E2B 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