@tuturetom What’s the typical DeepSeek V4.1 Flash inference speed on OpenDesign Go — specifically output tok/s and TTFT? Also, is inference speed the same across Go, Plus, Pro and Max?
@OpenDesignHQ What’s the typical DeepSeek V4.1 Flash inference speed on OpenDesign Go — specifically output tok/s and TTFT? Also, is inference speed the same across Go, Plus, Pro and Max?