allura-org/Q3-8B-Kintsugi

Full fine-tune vs Qwen/Qwen3-8B-Base. Fine-tune: 92% of the weights changed, across 36 of 36 layers.

Tensors changed: Embeddings 0/1, Norms 0/145, MLP 108/108, Attention 144/144, lm_head 1/1

2 derivatives checked

• mradermacher/Q3-8B-Kintsugi-i1-GGUF: Quantization
• mradermacher/Q3-8B-Kintsugi-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse