Welcome Beam: a 501B open model you can own, customize, and scale
Reflection, a new US lab, has released Beam, an open mixture-of-experts (MoEs) model with 501B parameters (23B active per token) on Hugging Face. Beam supports text input, features a 1M token context window, and is licensed under Apache 2.0. Its tokenizer includes a response template that parse_response uses to convert raw output into a structured message dictionary, separating reasoning, answers, and tool calls without relying on regular expressions.
Beam is the first open model from Reflection, and it features a 1M token context window, unlike many other open models.
Time & source
Times shown in UTC
Display time zone: UTC
Local time zone unavailable; showing UTC.
PublishedOffset at this time: UTC+0Oct 16, 2026, 00:00 UTC
IngestedOffset at this time: UTC+0Oct 16, 2026, 14:00 UTC
- Published
- Oct 16, 2026, 00:00
- Ingested
- Oct 16, 2026, 14:00
- Source type
- Official
- Tier
- First-party
- Source status
- Healthy
Tier is a per-source editorial setting, not a per-item score.
Discussion trend
The percentage is based on collected discussion signal, not new comments or independent people. The curve only compares the same topic across time.
Beam by Reflection is out on Hugging Face! It is the first model from the new US lab, Reflection, and it’s open! It's a mixture-of-experts (MoEs) model with 501B parameters (23B active per token), supports text as input, has a context window of 1M tokens, and is released under the Apache 2.0 license.
Beam is focused on coding and agentic use cases. It is for teams that want a frontier-scale model on their own hardware, infrastructure, or cloud, and want to customize it to their own use cases. Beam ships with its own dedicated open source Rust based harness that delivers the best performance from the model.
Beam has a native transformers implementation, as well as downstream libraries like vLLM and SGLang. We’ve worked with the Reflection team to bring you inference, SFT (supervised fine tuning), and RL (reinforcement learning) recipes for you to build with this model for your needs. On top of day-0 support in transformers, SGLang and vLLM, this post shows you how to run it, how to post-train it, and what we built with it.
TL;DR
- 501B-parameter MoEs LLM with 23B active per token. 52 layers, 256 experts per MoE layer, 8 routed per token.
- Text in, text out with context window of 1M tokens.
- Checkpoint formats: BF16 , FP8, and NVFP4
- Reasoning that can stay in context across turns (preserve_thinking), tool calling with a dedicated grammar. The model supports five reasoning values: "low", "medium" (default), "high", "xhigh", and "max".
- Response template in the tokenizer.
- Speculative decoding drafter model with DFlash2
- Day-0 libraries: transformers, SGLang, vLLM. Full-parameter RL with Miles.
- Ships with a Rust-based custom harness.
- Apache 2.0.
Build with Beam
Reflection is going to give out $10,000 Hub credits to the best projects that use Beam. All you have to do is make a thing, and share it on the Hub:
- You could make a demo that uses the Beam model on Spaces
- You could quantize it for your favorite hardware
- You could generate a synthetic dataset for your favorite problem
- You could build an RL environment with or for Beam
- You could benchmark Beam and share the results.
- You could surprise us!
If you build something with Beam, then share it on the Hub for a chance to win $10,000. All you have to do is build the space, model, or dataset repo and share it on the model’s repo page . We’ll collect all the links, select the best, and send out the credits to your Hub accounts.
What is Beam?
Beam is a text-only model built for long-context (1M context length) reasoning and agentic work. It is a sparse MoE model, where each token is computed by a small fraction of the network, so it runs at the speed of a much smaller model while keeping the capacity of a large one.