burtenshaw/Qwen3-30B-A3B-python-coder
Full fine-tune vs Qwen/Qwen3-30B-A3B. Fine-tune: 94% of the weights changed, across 48 of 48 layers.
Tensors changed: Embeddings 0/1, Norms 180/193, MLP 2613/2613, Attention 192/192, lm_head 1/1
3 derivatives checked
- mradermacher/Qwen3-30B-A3B-python-coder-i1-GGUF: Quantization
- mradermacher/Qwen3-30B-A3B-python-coder-GGUF: Quantization
- jerryzhao173985/Qwen3-30B-A3B-python-coder-mlx: Quantization
1 other repos hold byte-for-byte identical weight files.