NbAiLab/borealis-27b

Full fine-tune vs google/gemma-3-27b-it. Fine-tune: 98% of the weights changed, across 62 of 62 layers.

Tensors changed: Embeddings 1/4, Norms 288/484, MLP 186/294, Attention 248/464, other 0/1

1 derivatives checked

• NbAiLab/borealis-27b-gguf: Same weights, converted (fewer layers)

On the Hub · Downloads on Model Pulse