dmarsili/ExpertLens-Qwen3-VL-30B-A3B

Partial fine-tune vs Qwen/Qwen3-VL-30B-A3B-Instruct. Partial change: 72% of the weights changed (attention, lm_head, mlp, norms), in 48 of 48 layers.

Tensors changed: Embeddings 0/4, Norms 101/309, MLP 118/268, Attention 192/300, lm_head 1/1

2 derivatives checked

• mradermacher/ExpertLens-Qwen3-VL-30B-A3B-i1-GGUF: Quantization
• mradermacher/ExpertLens-Qwen3-VL-30B-A3B-GGUF: Quantization

On the Hub · Downloads on Model Pulse