DevQuasar-3/google.gemma-2b-aps-it-GGUF

Quantization vs google/gemma-2b-aps-it. DevQuasar-3/google.gemma-2b-aps-it-GGUF is a GGUF quantization (Q8_0) of the same weights: 37 tensors match exactly and 127 within quantization error.

Tensors changed: Embeddings 0/1, Norms 0/37, MLP 0/54, Attention 0/72

On the Hub · Downloads on Model Pulse