Step 3.7 Flash: A 196B MoE Model Built for Inference Efficiency
Fireworks AI(@FireworksAI_HQ)183 字 (约 1 分钟)
85
Step 3.7 Flash is a 196B MoE model designed from the ground up for inference efficiency, using MFA and AFD techniques to reduce KV-cache usage to ~22% of DeepSeek, supporting agent, coding, and multimodal workflows, open-sourced under Apache 2.0 and available on Fireworks.
入选理由：Step 3.7 Flash 是 196B MoE 模型，从设计之初就聚焦推理效率，而非事后优化。
FeaturedTweet#Step 3.7 Flash#MoE#Inference Optimization#Fireworks AI#Apache 2.0英文
