aifeifei798/DarkIdol-Qwen3.8-27B-v1.1

Full fine-tune vs Qwen/Qwen3.8-27B. Fine-tune: 93% of the weights changed, across 64 of 64 layers.

Tensors changed: Norms 0/325, Attention 305/560, MLP 193/307, Embeddings 1/5, lm_head 0/1, other 0/1

3 derivatives checked

• mradermacher/DarkIdol-Qwen3.8-27B-v1.1-GGUF: Quantization
• mradermacher/DarkIdol-Qwen3.8-27B-v1.1-i1-GGUF: Quantization
• Wiself/DarkIdol-Qwen3.8-27B-v1.1-Voice: Same weights, repacked (fewer layers)

On the Hub · Downloads on Model Pulse