sensenova/SenseNova-MARS-32B

Full fine-tune vs Qwen/Qwen3-VL-8B-Instruct. Fine-tune: 100% of the weights changed, across 36 of 36 layers.

Tensors changed: Norms 188/188, Attention 108/108, MLP 116/116, Embeddings 3/3

2 derivatives checked

• mradermacher/SenseNova-MARS-32B-i1-GGUF: Quantization (fewer layers)
• mradermacher/SenseNova-MARS-32B-GGUF: Quantization (fewer layers)

On the Hub · Downloads on Model Pulse