Model Releases

Many research labs only consider inference efficiency after the fact. Step 3.7 Flash is a 196B MoE model, and built for inference from the s…

Many research labs only consider inference efficiency after the fact. Step 3.7 Flash is a 196B MoE model, and built for inference from the start by @StepFun_ai. Multi-Matrix Factorization Attention (M

DGX agentx-post
model-releasesfireworks-ai--x

Many research labs only consider inference efficiency after the fact. Step 3.7 Flash is a 196B MoE model, and built for inference from the start by @StepFun_ai. Multi-Matrix Factorization Attention (MFA) → KV-cache at ~22% of DeepSeek. Attention-FFN Disaggregation (AFD) → decoupled attention + FFN for hardware-optimized serving. Try it now on Fireworks. Apache 2.0 license → http://fireworks.ai/models/fireworks/step-3p7-flash-nvfp4 ⚡️ Step 3.7 Flash is here: The new frontier is agent efficiency. #1 ClawEval-1.1 (67.1), #1 SimpleVQA Search (79.2), #2 SWE-PRO (56.3), 95.3 on V* Python. Open weights under Apache 2.0. Built for agentic, coding, search, and multimodal workflows — balancing speed, cost, and relia…

Source: Fireworks AI (X) | 2026-06-01

Loading related sources…