katanemo/Plano-Orchestrator-30B-A3B

Partial fine-tune vs Qwen/Qwen3-30B-A3B-Instruct-2507. Partial change: 88% of the weights changed (attention, mlp, norms), in 48 of 48 layers.

Tensors changed: Embeddings 0/1, Norms 141/193, MLP 2580/2613, Attention 192/192, lm_head 0/1

3 derivatives checked

• XythicK/Plano-Orchestrator-30B-A3B-GGUF: Quantization
• mradermacher/Plano-Orchestrator-30B-A3B-i1-GGUF: Quantization
• mradermacher/Plano-Orchestrator-30B-A3B-GGUF: Quantization

On the Hub · Downloads on Model Pulse