@huggingface: LIVE STREAM in minutes! Hear from the Reflection team about how they built Beam. Stream: https://youtube.com/watch?v=dG…
Summary
Hugging Face hosts a live stream with the Reflection team about how they built Beam, which is being released with open weights under Apache 2.0 in collaboration with 40+ partners, including weights, tokenizer, and reference implementation in BF16, FP8, and NVFP4 formats.
View Cached Full Text
Cached at: 10/16/26, 10:45 PM
LIVE STREAM in minutes! Hear from the Reflection team about how they built Beam. Stream: https://youtube.com/watch?v=dGhUFqeITbY…
@huggingface: LIVE STREAM in minutes! Hear from the Reflection team about how they built Beam. Stream: https://youtube.com/watch?v=dG…
Channel: @huggingface Source: https://www.youtube.com/watch?v=dGhUFqeITbY
Reflection (@reflection_ai): Beam is now available across platforms, with open weights under the Apache 2.0 license - in collaboration with an ecosystem of 40+ partners.
We’re releasing:
- Weights, tokenizer, and reference implementation
- BF16, FP8 and NVFP4 weights and a DFlash2 drafter
- The open source
Similar Articles
reflection/Beam-1.0-501B-A23B · Hugging Face
Reflection 发布开源模型 Beam-1.0-501B-A23B，采用稀疏 MoE 架构（501B 总参数/23B 激活参数），支持 1M token 上下文，主打 token 高效推理、软件工程与智能体工具调用能力，提供 BF16、FP8、NVFP4 多种数值精度版本，采用 Apache 2.0 许可。
Beam: Reflection's 501B open-weight model
Reflection AI introduced Beam, a 501B-parameter sparse MoE open-weight model (23B active) built for coding, reasoning, and agentic workloads, pretrained on 23.8T tokens and scaled with a high-compute RL run on 10.5K GB300 GPUs. Beam is positioned as advancing the Western open-weight frontier, approaching GLM 5.2 and Qwen 3.8-Max on coding/agentic tasks while using 3–4× less inference compute, with weights and a technical report due later this month.
Welcome Beam: a 501B open model you can own, customize, and scale
Reflection 开源发布 Beam 1.0，一个 501B 参数（23B 激活）的 MoE 大模型，支持 1M token 上下文、Apache 2.0 许可，并附带 Rust harness、vLLM/SGLang/transformers 第一天支持以及 SFT 和 RL 训练配方。
@rauchg: It’s time to -max. Beam is an American-made open-weight model by Reflection. And it’s now free on @vercel AI Gateway. P…
Reflection 的美国制造开源权重模型 Beam 此前以 stealth/cat-jam 名义运行，现已在 Vercel AI Gateway 上限时免费提供，主打低延迟，可接入 Eve agents 和编码工具使用。
@TheAhmadOsman: Congrats to all the friends at Reflection We now have a SoTA American Opensource model
Congrats to Reflection AI on releasing Beam, a highly efficient agentic open model with 501B total parameters and 23B active, advancing the Western open-source frontier in coding and agentic tasks.