NousResearch/nomos-1

Full fine-tune vs Qwen/Qwen3-30B-A3B-Thinking-2507. Fine-tune: 100% of the weights changed, across 48 of 48 layers.

Tensors changed: Embeddings 1/1, Norms 193/193, MLP 2613/2613, Attention 192/192, lm_head 1/1

1 derivatives checked

• DevQuasar/NousResearch.nomos-1-GGUF: Quantization

On the Hub · Downloads on Model Pulse