Tung111/OPOD-Qwen3-Omni-30B-A3B
Partial fine-tune vs Qwen/Qwen3-Omni-30B-A3B-Instruct. Partial change: 79% of the weights changed (attention, embeddings, lm_head, mlp, norms, other), in 48 of 48 layers.
Tensors changed: other 11/148, MLP 1055/1557, Norms 257/562, Attention 555/696, Embeddings 3/21, lm_head 1/16
2 derivatives checked
- mradermacher/OPOD-Qwen3-Omni-30B-A3B-i1-GGUF: Quantization
- mradermacher/OPOD-Qwen3-Omni-30B-A3B-GGUF: Quantization