mradermacher/CyberGemma-3-4b-merged-GGUF

Same weights, converted (fewer layers) vs MaestroDev19/CyberGemma-3-4b-merged. mradermacher/CyberGemma-3-4b-merged-GGUF matches part of MaestroDev19/CyberGemma-3-4b-merged (444 of its 883 tensors; the rest of MaestroDev19/CyberGemma-3-4b-merged has no counterpart). On the shared part: Same weights stored in another dtype (F16/BF16 → F16/F32).

Tensors changed: Embeddings 0/1, Norms 0/205, MLP 0/102, Attention 0/136

On the Hub · Downloads on Model Pulse