nightmedia/Qwen3.5-9B-Theseus

Full fine-tune vs OrionLLM/OxCoder-9B. Fine-tune: 100% of the weights changed, across 32 of 32 layers.

Tensors changed: lm_head 1/1, Embeddings 4/4, Norms 215/215, Attention 332/332, MLP 208/208

2 derivatives checked

• mradermacher/Qwen3.5-9B-Theseus-i1-GGUF: Quantization
• mradermacher/Qwen3.5-9B-Theseus-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse