gghfez/gemma-3-4b-novision
Same weights, repacked (fewer layers) vs google/gemma-3-4b-it. gghfez/gemma-3-4b-novision matches part of google/gemma-3-4b-it (444 of its 883 tensors; the rest of google/gemma-3-4b-it has no counterpart). On the shared part: Same weights in different files (re-saved, re-sharded or new metadata).
Tensors changed: Embeddings 0/1, Norms 0/205, MLP 0/102, Attention 0/136
4 derivatives checked
- mradermacher/gemma-3-4b-novision-i1-GGUF: Quantization
- mradermacher/gemma-3-4b-novision-GGUF: Same weights, converted
- tensorblock/gghfez_gemma-3-4b-novision-GGUF: Quantization
- lunahr/gemma-3-4b-abliterated: Abliterated
6 other repos hold byte-for-byte identical weight files.