tensorblock/gemma-3-4b-it-GGUF

Quantization (fewer layers) vs google/gemma-3-4b-it. tensorblock/gemma-3-4b-it-GGUF matches part of google/gemma-3-4b-it (443 of its 883 tensors; the rest of google/gemma-3-4b-it has no counterpart). On the shared part: tensorblock/gemma-3-4b-it-GGUF is a GGUF quantization (Q3_K_M) of the same weights: 205 tensors match exactly and 238 within quantization error.

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

On the Hub · Downloads on Model Pulse