Model ID
stepfun-ai/Step-3.7-Flash
Capabilities
Step 3.7 Flash
Step 3.7 Flash is a multimodal sparse Mixture-of-Experts (MoE) model designed for high-throughput reasoning, coding, and agentic workflows with native image understanding. It features 198B total parameters with approximately 11B activated per token, using a 45-layer transformer with 4,096 hidden size, 64 attention heads, and 288 experts activating 8 per token. The model combines a hybrid sliding-window and full-attention architecture with a dedicated vision encoder and Multi-Token Prediction, supporting up to a 256K context window for efficient long-context multimodal inference.
About this model
Step 3.7 Flash is a multimodal sparse Mixture-of-Experts (MoE) model designed for high-throughput reasoning, coding, and agentic workflows with native image understanding. It features 198B total parameters with approximately 11B activated per token, using a 45-layer transformer with 4,096 hidden size, 64 attention heads, and 288 experts activating 8 per token. The model combines a hybrid sliding-window and full-attention architecture with a dedicated vision encoder and Multi-Token Prediction, supporting up to a 256K context window for efficient long-context multimodal inference.
Model specifications and capabilities are published by the model author and reproduced here from HF Model Card (stepfun-ai/Step-3.7-Flash). Released under Apache 2.0. Further reading: Blog
Deploy Private Inference Endpoint
Choose your hardware and inference engine to get deployment commands and performance benchmarks tailored to your infrastructure
Hardware
B200
1,440 GB
Engine
vLLM
SGLang
Llama.cpp
Deployment code
Access Restricted
Enter your email to get access to this content
Performance under load
Tokens/s (total)
Benchmarks measured by Vultr on B200 · vLLM. Throughput and latency vary with concurrency, input length and engine configuration, so treat these as a comparison baseline, not a service guarantee.
NVIDIA HGX B200
Unlock Next-Generation AI Power on Vultr Cloud GPU