Lambent/Zora-9B-v0

Full fine-tune vs EganAI/qwen3.5-9b-terminal-merge. Fine-tune: 95% of the weights changed, across 32 of 32 layers.

Tensors changed: lm_head 1/1, Embeddings 1/4, Norms 105/215, Attention 224/332, MLP 96/208

3 derivatives checked

• mradermacher/Zora-9B-v0-i1-GGUF: Quantization
• mradermacher/Zora-9B-v0-GGUF: Same weights, converted
• Lambent/Zora-9B-v1: Partial fine-tune

On the Hub · Downloads on Model Pulse