yamatazen/Qwen3-V-Science-14B-v2

Full fine-tune vs ValiantLabs/Qwen3-14B-Esper3. Fine-tune: 100% of the weights changed, across 40 of 40 layers.

Tensors changed: Embeddings 1/1, Norms 139/161, MLP 120/120, Attention 160/160, lm_head 1/1

2 derivatives checked

• mradermacher/Qwen3-V-Science-14B-v2-i1-GGUF: Quantization
• mradermacher/Qwen3-V-Science-14B-v2-GGUF: Quantization

On the Hub · Downloads on Model Pulse