OusiaResearch/Aureth-4B-Qwen3.5

Full fine-tune vs Qwen/Qwen3.5-4B. Fine-tune: 93% of the weights changed, across 32 of 32 layers.

Tensors changed: Embeddings 2/4, MLP 100/196, Attention 201/320, Norms 107/203

3 derivatives checked

• mradermacher/Aureth-4B-Qwen3.5-i1-GGUF: Quantization
• mradermacher/Aureth-4B-Qwen3.5-GGUF: Same weights, converted
• Auguments/Aureth-4B-Qwen3.5-Heretic: Abliterated

On the Hub · Downloads on Model Pulse