DevQuasar-12/google.gemma-3-1b-it-qat-int4-unquantized-GGUF

Same weights, converted vs google/gemma-3-1b-it-qat-int4-unquantized. Same weights stored in another dtype (BF16 → F16/F32).

Tensors changed: Embeddings 0/1, Norms 0/157, MLP 0/78, Attention 0/104

On the Hub · Downloads on Model Pulse