MoonRide/gemma-4-E4B-it-heretic-ara-GGUF

Same weights, converted (fewer layers) vs MoonRide/gemma-4-E4B-it-heretic-ara. MoonRide/gemma-4-E4B-it-heretic-ara-GGUF matches part of MoonRide/gemma-4-E4B-it-heretic-ara (623 of its 2076 tensors; the rest of MoonRide/gemma-4-E4B-it-heretic-ara has no counterpart). On the shared part: Same weights stored in another dtype (BF16 → BF16/F32), plus 43 new tensors.

Tensors changed: Embeddings 0/2, Norms 0/278, MLP 0/126, other 0/85, Attention 0/132

On the Hub · Downloads on Model Pulse