inclusionAI/UI-Venus-2-9B
Full fine-tune vs Qwen/Qwen3.5-9B. Fine-tune: 95% of the weights changed, across 32 of 32 layers.
Tensors changed: lm_head 1/1, Embeddings 1/4, MLP 96/208, Attention 193/332, Norms 83/215
4 derivatives checked
- bartowski/UI-Venus-2-9B-GGUF: Same weights, converted
- prithivMLmods/inclusionAI-UI-Venus-2-9B-GGUF: Same weights, converted
- mradermacher/UI-Venus-2-9B-GGUF: Same weights, converted
- nightmedia/Qwen3.5-9B-Continuum-mxfp8-mlx: Quantization