Step 3.7 Flash 的总参数规模，采用稀疏 MoE 架构以优化推理效率。

198B 还有哪些别名？

198B 也被称为：198B Model。

What is 198B? | AI Glossary

Q: 198B 最近有什么新动态？

traeai 已收录 1 篇与 198B 相关的内容。最新一篇是「Many research labs only consider inference efficiency after the fact. Step 3.7 Flash is a 198B spars...」，由 Fireworks AI(@FireworksAI_HQ) 发布。

Fireworks AI on X: "Many research labs only consider inference efficiency after the fact. Step 3.7 Flash is a 198B sparse MoE VLM designed by @StepFun_ai for inference from the start. 196B language backbone with a 1.8B vision encoder. Built for real-world agent workloads, running at up to 400 ..."

Fireworks AI(@FireworksAI_HQ)Yesterday112 字 (约 1 分钟)

Fireworks AI introduces Step 3.7 Flash: a 198B sparse MoE VLM designed for inference from the start, with a 196B language backbone and 1.8B vision encoder, achieving up to 400 token/s on real-world agent workloads.

入选理由：从设计阶段即优化推理效率，非事后补强。

FeaturedTweet#Step3.7 Flash#sparse MoE#VLM#198B#400 token/s英文

什么是 198B？

📰 198B 最新动态

Fireworks AI on X: "Many research labs only consider inference efficiency after the fact. Step 3.7 Flash is a 198B sparse MoE VLM designed by @StepFun_ai for inference from the start. 196B language backbone with a 1.8B vision encoder. Built for real-world agent workloads, running at up to 400 ..."

什么是 198B？

📰 198B 最新动态

Fireworks AI on X: "Many research labs only consider inference efficiency after the fact. Step 3.7 Flash is a 198B sparse MoE VLM designed by @StepFun_ai for inference from the start. 196B language backbone with a 1.8B vision encoder. Built for real-world agent workloads, running at up to 400 ..."

🔗 相关术语