clzoro/Qwen3.5-122B-A10B-Claude-distill

Partial fine-tune vs Qwen/Qwen3.5-122B-A10B. Partial change: 80% of the weights changed (attention, lm_head, mlp, norms), in 48 of 48 layers.

Tensors changed: lm_head 1/1, Embeddings 0/4, Attention 279/444, MLP 234/352, Norms 101/267

2 derivatives checked

• mradermacher/Qwen3.5-122B-A10B-Claude-distill-i1-GGUF: Quantization
• mradermacher/Qwen3.5-122B-A10B-Claude-distill-GGUF: Quantization

On the Hub · Downloads on Model Pulse