From the source
Reflection AI introduced Beam, an open-weight sparse mixture-of-experts model for agentic coding and long-horizon tasks, with 501 billion total parameters and 23 billion active parameters.
The model is available in Amazon SageMaker JumpStart in two US East regions, and its weights are released on
Hugging Face under the Apache 2.0 license in BF16, FP8, and NVFP4 checkpoint variants.
The post provides deployment guidance for SageMaker JumpStart real-time endpoints and SageMaker HyperPod Inference.