在预发布的 @DeepInfra 端点上以 NVFP4 权重进行测量，Nemotron 3.5 Super VL 在 100k token 提示词下达到约 630 tokens/s 的输出速度。这是我们在该提示词长度下测得的、Intelligence Index 得分 20 及以上的所有模型中最快的。 约为 Inkling Small（124 tokens/s）的 5 倍、Nemotron 3 Ultra（235）的 2.7 倍、Nemotron 3 Super（140）的 4.5 倍。其首 token 返回时间为 1.8s，而 Nemotron 3 Ultra 为 4.4s，Inkling Small 为 8.5s。
Measured on a pre-release @DeepInfra endpoint serving NVFP4 weights, Nemotron 3.5 Super VL reaches an output speed of ~630 tokens/s with 100k-token prompts. That is the fastest of any model scoring 20 or more on the Intelligence Index that we have measured at this prompt length
That is ~5x Inkling Small (124 tokens/s), ~2.7x Nemotron 3 Ultra (235), and ~4.5x Nemotron 3 Super (140). It also returns its first token in 1.8s, against 4.4s for Nemotron 3 Ultra and 8.5s for Inkling Small
来源：Artificial Analysis · x.com