xxang/AStar-Thought-V2-Qwen3.6-27B

Full fine-tune vs Qwen/Qwen3.6-27B. Fine-tune: 98% of the weights changed, across 64 of 64 layers.

Tensors changed: MLP 192/304, Attention 374/556, Norms 145/319, Embeddings 0/3

1 derivatives checked

• mradermacher/AStar-Thought-V2-Qwen3.6-27B-GGUF: Quantization

On the Hub · Downloads on Model Pulse