Mungert/gemma-4-31B-it-GGUF

Full fine-tune (fewer layers) vs google/gemma-4-31B. Mungert/gemma-4-31B-it-GGUF matches part of google/gemma-4-31B (772 of its 1188 tensors; the rest of google/gemma-4-31B has no counterpart). On the shared part: Mungert/gemma-4-31B-it-GGUF is a GGUF (Q8_0) of different weights. Fine-tune: 100% of the weights changed, across 60 of 60 layers.

Tensors changed: Embeddings 1/1, Norms 208/361, MLP 180/180, Attention 230/230

On the Hub · Downloads on Model Pulse