Reflection releases Beam open MoE model
Trending storyDeveloping
Reflection releases Beam open MoE model
1 reports1 sourcesUpdated 15 hours ago
What you need to know
AI summary
Reflection released Beam, its first model: a 501B-parameter mixture-of-experts LLM with 23B active parameters per token, a 1M-token context window, and an Apache 2.0 license. The model is open-weight, and the 23B active-parameter figure means only that portion of the 501B total is used per token during inference.
Generated by AI from the reporting · updated 1 hour ago
Latest updateOct 16 00:00
Reflection releases Beam, a 501B open MoE model with 1M context under Apache 2.0Timeline
Follow the reports to see every side of the story.
Oct 16
- Hugging Face BlogFeaturedReflection releases Beam, a 501B open MoE model with 1M context under Apache 2.0
Reflection released Beam, its first model, a 501B-parameter mixture-of-experts LLM with 23B active parameters per token.
Heat trend for this story
Not enough continuous data yet to chart a trend.