groxaxo/Qwen-AgentWorld-35B-A3B-GGUF

Same weights, converted vs Qwen/Qwen-AgentWorld-35B-A3B. Same weights stored in another dtype (BF16 → BF16/F32), plus 150 new tensors.

Tensors changed: MLP 0/200, Attention 0/40, Norms 0/101, Embeddings 0/1, lm_head 0/1

On the Hub · Downloads on Model Pulse