sii-research/InnoSpark3.0-9B-260630

Full fine-tune vs Qwen/Qwen3.5-9B. Fine-tune: 93% of the weights changed, across 32 of 32 layers.

Tensors changed: lm_head 1/1, Embeddings 1/5, MLP 96/211, Attention 187/336, other 0/1, Norms 80/221

2 derivatives checked

• mradermacher/InnoSpark3.0-9B-260630-i1-GGUF: Quantization
• mradermacher/InnoSpark3.0-9B-260630-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse