Reflection's Beam, a 501B-parameter open MoE model with 1M context, lands on Hugging Face under Apache 2.0
QGallouedec · x · 2026-10-16
- Beam, the first model from new US lab Reflection, is now on Hugging Face under Apache 2.0, fully open.
- Architecture: MoE with 501B total parameters, 23B active per token; 52 layers, 256 experts per MoE layer with 8 routed per token; checkpoints in BF16, FP8, and NVFP4.
- Context: 1M tokens, text-in/text-out.
- Positioning: built for coding and agentic use cases — teams wanting frontier-scale capability on their own hardware, infrastructure, or cloud. Ships with a dedicated open-source Rust-based inference harness.
- Reasoning controls: five levels ("low" to "max"), cross-turn thinking preservation via preservethinking, and grammar-constrained tool calling.
- Ecosystem: day-0 support in transformers, vLLM, and SGLang; full-parameter RL via Miles; SFT and RL recipes provided; speculative decoding drafter model DFlash2.
Related event: Reflection AI open-sources 501B MoE model Beam with 40+ partner ecosystem(19 posts)→
More from coding & agent
- Why company AI agents go stale: adoption needs in-house knowledge, not just better agents — EdenEmarco177 · 2026-10-16
- Open-source MCP lets coding agents search Obsidian's 9,000-plugin directory before reinventing wheels — pitfa19 · 2026-10-16
- Cheng Lou open-sources Handwired: hand-written weights turn code into training-free neural nets — dotey · 2026-10-16
- Building a portable context vault in Notion so every AI agent knows you from day one — ivanhzhao · 2026-10-16
- Lovable apps can now talk to customers on WhatsApp with inbox, reminders and templates — AlexandrePesant · 2026-10-16
- Stanford HAI: AI coding agents fail at teamwork — 233C · 2026-10-16