Skywork/MindLink-32B-0801
Full fine-tune vs Qwen/Qwen3-32B. Fine-tune: 100% of the weights changed, across 64 of 64 layers.
Tensors changed: Embeddings 1/1, Norms 245/257, MLP 192/192, Attention 256/256, lm_head 1/1
6 derivatives checked
- bartowski/Skywork_MindLink-32B-0801-GGUF: Same weights, converted
- mradermacher/MindLink-32B-0801-i1-GGUF: Quantization
- gabriellarson/MindLink-32B-0801-GGUF: Same weights, converted
- mradermacher/MindLink-32B-0801-GGUF: Quantization
- lmstudio-community/MindLink-32B-0801-GGUF: Quantization
- DevQuasar/Skywork.MindLink-32B-0801-GGUF: Same weights, converted