Gryphe/Qwen3.6-35B-A3B-StyleTune

Partial fine-tune vs Qwen/Qwen3.6-35B-A3B. Partial change: 1% of the weights changed (lm_head), in 0 of 40 layers.

Tensors changed: Embeddings 0/4, Attention 0/388, MLP 0/392, Norms 0/241, lm_head 1/1

3 derivatives checked

• mradermacher/Qwen3.6-35B-A3B-StyleTune-i1-GGUF: Quantization
• mradermacher/Qwen3.6-35B-A3B-StyleTune-GGUF: Quantization
• Wiself/Qwen3.6-35B-A3B-StyleTune-Voice: Same weights, repacked (fewer layers)

On the Hub · Downloads on Model Pulse