English translation is being prepared.
View original postEnglish translation is being prepared.
View original
685 output tokens/s per user on @Alibaba_Qwen Qwen3.8-Flash-Next. Running TokenSpeed on 4× NVIDIA GB300 with NVFP4. A look at the kernel and serving optimizations behind the results: 👉 https://t.co/ngSITTWNai ⭐ https://t.co/MJzhCEg7m8 https://t.co/CmIBYUTm5M
Body
The English body is being prepared. You can open the original source.