تەلارسازی، بەهێزییەکان و بەکارهێنان
Kanana 2 30B-A3B Thinking 2601 is an official self-hostable Kakao release in the Kanana Reasoning track. It uses DeepseekV3ForCausalLM, carries 30B / 3B MoE, supports a verified context window of 32,768 تۆکنەکان, and exposes only source-certified خاڵەکانی وەشان and ژینگەی جێبەجێکردن combinations. Its release, license and deployment facts are tied to the official repository revision rather than inferred from the family name.
Kanana 2 30B-A3B Thinking 2601 uses DeepseekV3ForCausalLM with 30B / 3B MoE. The stored architecture profile records 48 layers, hidden width 2048, 32 attention heads and a 32,768 تۆکن context ceiling where the official configuration publishes those fields.
Verified DeepseekV3ForCausalLM architecture
32,768 تۆکن certified context
Official BF16 خاڵی وەشان coverage
Private LLM inference
Agentic workflows
Long-context document processing