Agents
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 in…
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 v
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 tok/sec. Native multimodal understanding and action, reliable tool use, and enhanced web and visual search. Apache 2.0. Try it now → https://fireworks.ai/models/fireworks/step-3p7-flash-nvfp4
Source: Fireworks AI (X) | 2026-06-04