nightmedia/Qwen3-4B-Element18

Full fine-tune vs Alibaba-Apsara/DASD-4B-Thinking. Fine-tune: 100% of the weights changed, across 36 of 36 layers.

Tensors changed: Embeddings 1/1, Norms 145/145, MLP 108/108, Attention 144/144

2 derivatives checked

• mradermacher/Qwen3-4B-Element18-i1-GGUF: Quantization
• mradermacher/Qwen3-4B-Element18-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse