allura-org/Qwen3.6-35B-A3B-Anko

Full fine-tune vs Qwen/Qwen3.6-35B-A3B. Fine-tune: 97% of the weights changed, across 40 of 40 layers.

Tensors changed: Embeddings 0/1, Attention 130/280, MLP 80/280, Norms 0/131, lm_head 0/1

3 derivatives checked

• bartowski/allura-org_Qwen3.6-35B-A3B-Anko-GGUF: Same weights, converted
• mradermacher/Qwen3.6-35B-A3B-Anko-i1-GGUF: Quantization
• mradermacher/Qwen3.6-35B-A3B-Anko-GGUF: Quantization

On the Hub · Downloads on Model Pulse