PulseAugur
中
实时 00:27:46
한국어(KO) Qwen팀이 Qwen3.8-Flash-Next 가중치를 공개했습니다. 멀티모달 MoE 모델로 Gated DeltaNet+Qwen Sparse Attention(GDN+QSA) 하이브리드, Gated Residual, N-gram 임베딩, Muon 옵티마이저 등을 도입해 성능은 올리고 연

Qwen发布Qwen3.8-Flash-Next多模态MoE模型，支持1M上下文

作者 PulseAugur 编辑部 · [1 个来源] ·

Qwen团队发布了其Qwen3.8-Flash-Next模型的权重，这是一款多模态混合专家（MoE）架构模型。该新模型集成了多项创新，如Gated DeltaNet+Qwen Sparse Attention (GDN+QSA)混合、Gated Residual Networks、N-gram embedding和Muon优化器，旨在提高性能同时降低计算和训练成本。该模型支持262,144个token的基础上下文长度，可通过YaRN扩展至100万token，其权重可在Hugging Face和ModelScope上获取。 AI

影响 此次发布提供了更高的效率和显著更大的上下文窗口，可能支持更复杂的多模态应用。

排序理由 Qwen发布了带有系统卡的模型。 [lever_c_demoted from frontier_release: ic=1 ai=1.0]

在 Mastodon — fosstodon.org 阅读 →

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

Qwen发布Qwen3.8-Flash-Next多模态MoE模型，支持1M上下文

本文如何被排名

Signal score
18 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Significant
Qwen发布了带有系统卡的模型。 [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. Mastodon — fosstodon.org TIER_1 한국어(KO) · [email protected] ·

    Qwen团队发布Qwen3.8-Flash-Next权重，引入多模态MoE模型，采用Gated DeltaNet+Qwen Sparse Attention (GDN+QSA)混合结构、Gated Residual、N-gram embedding及Muon优化器以提升性能并降低计算量。

    Qwen팀이 Qwen3.8-Flash-Next 가중치를 공개했습니다. 멀티모달 MoE 모델로 Gated DeltaNet+Qwen Sparse Attention(GDN+QSA) 하이브리드, Gated Residual, N-gram 임베딩, Muon 옵티마이저 등을 도입해 성능은 올리고 연산·학습 비용은 크게 절감했습니다. 핵심 모델은 125B 파라미터(추가 51B N-gram), 기본 262,144토큰 지원·YaRN으로 1M 확장 가능. 가중치는 Hugging Face·ModelScope에 공개되며…

    链接 qwen.ai/blog qwen.ai/blog

相关实体

相关话题