Nifer is insane. 700t/s with Qwen 3.6 35B (no thinking). Purpose build for RTX5090. Full 250k context too.

I just managed to get it running on windows and this thing is fucking insane. I get around 550-720t/s depending on task at hand. Previously to get to such numbers i would have to do batching and agents in parallel. Here it just does single instance at this insane speed. Couple that with No thi

中文全文翻译正在补齐，可先查看下方英文原文。

I just managed to get it running on windows and this thing is fucking insane. I get around 550-720t/s depending on task at hand. Previously to get to such numbers i would have to do batching and agents in parallel. Here it just does single instance at this insane speed. Couple that with No thi