ToastyPigeon/Qwen3-16B-A3B-MixedData

Full fine-tune vs Columbidae/Qwen3-16B-A3B-Base. Fine-tune: 94% of the weights changed, across 48 of 48 layers.

Tensors changed: Embeddings 0/1, Norms 117/193, MLP 2613/2613, Attention 192/192, lm_head 1/1

1 derivatives checked

• mradermacher/Qwen3-16B-A3B-MixedData-i1-GGUF: Quantization

On the Hub · Downloads on Model Pulse