DevQuasar/Qwen.Qwen-AgentWorld-35B-A3B-GGUF

Same weights, converted (fewer layers) vs Qwen/Qwen-AgentWorld-35B-A3B. DevQuasar/Qwen.Qwen-AgentWorld-35B-A3B-GGUF matches part of Qwen/Qwen-AgentWorld-35B-A3B (3 of its 693 tensors; the rest of Qwen/Qwen-AgentWorld-35B-A3B has no counterpart). On the shared part: Same weights stored in another dtype (BF16 → F16/F32).

Tensors changed: Embeddings 0/1, lm_head 0/1, Norms 0/1

On the Hub · Downloads on Model Pulse