LiamLian0727/Qwen3VL_Euclid_30B

Full fine-tune vs Qwen/Qwen3-VL-30B-A3B-Instruct. Fine-tune: 99% of the weights changed, across 48 of 48 layers.

Tensors changed: Embeddings 3/4, Norms 183/309, MLP 250/268, Attention 300/300, lm_head 1/1

2 derivatives checked

• mradermacher/Qwen3VL_Euclid_30B-i1-GGUF: Quantization
• mradermacher/Qwen3VL_Euclid_30B-GGUF: Quantization

On the Hub · Downloads on Model Pulse