soyrsoyr/gemma-4-unified-0.8B-tiny

Different architecture vs google/gemma-4-12B-it. Different architecture: only 27 of 677/96 tensors match by name and shape.

1 derivatives checked

• mradermacher/gemma-4-unified-0.8B-tiny-GGUF: Same weights, converted

1 other repos hold byte-for-byte identical weight files.

On the Hub · Downloads on Model Pulse