đ Qwen3.8-2.4T-A95B is Day-0 live on
@Bitdeer_AI Model Studio!
đđĨŗ
@Alibaba_Qwen! Releasing this 2.4T Max-class open-weights monster (95B active/token, 512 experts MoE). âī¸
đ 256K context
đ
@OpenAI-compatible + Parallel Tool Calls
đ reasoning_effort: tune (low/medium/xhigh) to balance depth vs. cost
đ§ preserve_thinking: keeps reasoning state across multi-turn chats
đ Run It Now: