mradermacher/gemma-4-unified-0.8B-tiny-GGUF

Same weights, converted vs soyrsoyr/gemma-4-unified-0.8B-tiny. Same weights stored in another dtype (BF16 → F16/F32), plus 7 new tensors.

Tensors changed: Embeddings 0/1, Norms 0/37, MLP 0/18, Attention 0/23

On the Hub · Downloads on Model Pulse