bgg1996/Melinoe-Qwen3-8-27B-VL

Full fine-tune vs Qwen/Qwen3.8-27B. Fine-tune: 94% of the weights changed, across 64 of 64 layers.

Tensors changed: Norms 130/325, Attention 360/560, MLP 195/307, Embeddings 0/5, lm_head 1/1, other 1/1

2 derivatives checked

• spiritfather/Melinoe-Qwen3-8-27B-VL-GGUF: Quantization
• spiritfather/Melinoe-Qwen3-8-27B-VL-i1-GGUF: Quantization

On the Hub · Downloads on Model Pulse