arXiv 2610.24628 · cs.CL · 2026-10-17
Muse Glimmer 30B: An On-Device Agentic Model
Arash Ebrahim Abtahizadeh, Muna Aghamelu, Adil Ahmed, Juan C. Angeles Acuna, Alexis Audran-Reiss, Asaf Avrahamy, Yoram Bachrach, Can Balioglu 等 329 人
Meta
在最新榜 #360 本站收录于 2026-10-26
一句话要点
Muse Glimmer 是开源的 300 亿参数端侧智能体模型，支持文本和图片输入，量化到约 4 比特后可在单张消费级 GPU 上运行，在同尺寸工具调用和多步规划评测上领先，采用 Apache 2.0 许可。
Muse Glimmer is an open-source 30B on-device agentic model with text and image input, quantized to about 4-bit for single consumer-GPU inference, claiming state-of-the-art agentic results for its size, released under Apache 2.0.
阅读 arXiv 原文 PDF Hugging Face 讨论
主题与学科
同主题：智能体
- Raven: The Harness of Harnesses for Composable Agentic Intelligence ▲748
- False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents ▲642
- Omni-IO Skills: Harnessing Your Agent Omni-Native ▲485
- BizAgentBench: Unveiling Hidden Challenges in Deploying Long-Horizon Agents for Real-World Business ▲388
- Player-1: Learning to Play from Synthetic Experience ▲347
同主题：大语言模型
- Jeva: System One Models from First Principles 2026-10-13 · ▲371
- Post-Training Leaves Behavioral Shadows on Unrelated Decisions 2026-09-24 · ▲273
- WeVisOne-VL: Unified Visual Perception from Objects to Pixels 2026-10-22 · ▲247
- Thinking Inertia: LLMs Keep Thinking When Told Not To 2026-10-08 · ▲241
- OmniEdu: Open Foundation Models for Learning and Teaching 2026-09-19 · ▲240
同机构：Meta
- Native Action-Prior Learning from Videos for World Action Models 2026-10-02
- Sharpening Tax in Post-Training 2026-10-01
- World Action Modeling with Progressive Visual Planning 2026-10-01
- Context Language Models 2026-09-29
数据说明
元数据来自 arXiv API（已核实）；点赞来自 Hugging Face 每日论文；引用来自 Semantic Scholar。最近刷新 2026-10-26。
要点由本站根据摘要自写，不转载摘要原文，请阅读原文。