miromind-ai/MiroThinker-v1.0-30B
Full fine-tune vs Qwen/Qwen3-30B-A3B-Thinking-2507. Fine-tune: 100% of the weights changed, across 48 of 48 layers.
Tensors changed: Embeddings 1/1, Norms 144/193, MLP 2613/2613, Attention 192/192, lm_head 1/1
5 derivatives checked
- bartowski/miromind-ai_MiroThinker-v1.0-30B-GGUF: Same weights, converted
- mradermacher/MiroThinker-v1.0-30B-i1-GGUF: Quantization
- mradermacher/MiroThinker-v1.0-30B-GGUF: Quantization
- DevQuasar/miromind-ai.MiroThinker-v1.0-30B-GGUF: Same weights, converted
- MaziyarPanahi/MiroThinker-v1.0-30B-GGUF: Same weights, converted