Reflection releases Beam, a 501B open MoE model for coding and agents
Original titleWelcome Beam: a 501B open model you can own, customize, and scale
AISummary
Reflection has released Beam, a 501B-parameter mixture-of-experts model with 23B active parameters per token, under the Apache 2.0 license.
It supports a 1M-token context window and targets coding and agentic use, with day-0 support in transformers, SGLang, and vLLM. The post also provides checkpoints in BF16, FP8, and NVFP4, plus inference, SFT, and RL recipes and a Hub credit program for projects built on Beam.
AIWhy it matters
The post gives architecture, hardware sizing, and serving recipes that let teams judge whether Beam fits their own infrastructure and customization plans.
Source: Hugging Face Blog · huggingface.coPublished · added here