PulseAugur
中
实时 16:47:53
English(EN) Reflection's Beam is open: 23B active, but you still have to fit 501B

Reflection 发布 5010亿参数开放权重模型 Beam,支持100万上下文

Reflection 发布了其新的开放权重模型 Beam,该模型采用稀疏专家混合架构,总参数量为5010亿,每个 token 活跃参数量为230亿。该模型拥有100万 token 的上下文窗口,并根据宽松的 Apache 2.0 许可证发布,允许商业使用且无限制性条款。虽然 Beam 为自托管提供了巨大潜力,特别是由于其声称的 token 效率而适用于编码代理,但用户应注意其内存需求巨大,需要多 GPU 设置,并且基准测试目前是自行报告的。 AI

影响 以其大型上下文窗口和宽松的许可为开放权重模型树立了新标杆,可能促进更多自托管的 AI 应用。

排序理由 Frontier-lab 模型发布,附带系统卡和宽松许可。[lever_c_demoted from frontier_release: ic=1 ai=1.0]

在 dev.to — LLM tag 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →

Reflection 发布 5010亿参数开放权重模型 Beam,支持100万上下文

本文如何被排名

Signal score
42 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Significant
Frontier-lab 模型发布,附带系统卡和宽松许可。[lever_c_demoted from frontier_release: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
model release, infra
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Breaking (< 6h)
Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

  1. dev.to — LLM tag TIER_1 English(EN) · Clydara ·

    Reflection's Beam 已开放:23B 活跃,但仍需容纳 501B

    <p>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.</p> <p>Most posts stoppe…