Reflection's Beam is open: 23B active, but you still have to fit 501B

Automated excerpt

Reflection released the weights for Beam on October 16, 2026. It is the lab's first open-weight model: a sparse mixture-of-experts (MoE) model with 501B total parameters, about 23B active per token, a 1M-token context window, and an Apache 2. 0 license. Knowledge cutoff: June 30, 2026 (model card).

Selected automatically from source text; not independently written or fact-checked. Read the original for full context.