AITOPAI热报
ModelsSelected

Muse Glimmer 30B 开源模型上线 Hugging Face

Official accountSimon Willison@simonw
Post
View the post
Why we picked it

新出的 Muse Glimmer 是 30B 开源模型，Apache 2.0 随便用，24GB 显存就能跑，做智能体应用可以直接拿来试。

Muse Glimmer 是参数量 30B 的智能体模型，以 Apache 2.0 协议开放权重。

Image · Simon Willison
Body

该模型可在 24GB 显存上运行，并保持智能体任务的可靠性。Hugging Face 上已提供 GGUF 量化版本供下载。

同一公告还预告了 Muse Spark 1.2 的开放权重版本即将推出。

Original · Simon Willison

Muse Glimmer, the new 30B model, is available on Hugging Face right now - here's the GGUF version: huggingface.co/meta-models/Mu… Alexandr Wang @alexandr_wang 1/ big announcement today: we will be releasing an open weight version of muse spark 1.2 soon. we also are releasing muse glimmer, a 30B agentic model with open weights under apache 2.0. muse glimmer can run on 24GB of VRAM without losing agentic reliability. 🧵 🔗 View Quoted Tweet📊 22 ⚡

Industry Coordinates & Source Verification

This report is categorized under AITOP's "Models" desk. Key entities and technical topics under continuous tracking include Muse Glimmer, Hugging Face, 开源模型, 智能体.

Source attribution: curated from Simon Willison (@simonw).

#Muse Glimmer#Hugging Face#开源模型#智能体

Keep reading

Recent stories with the same tag or section
ModelsBuildersMulti-sourceSelected16:36
Muse Glimmer 30B: Meta's distilled agent model runs on one consumer GPU

Distilling from a large teacher into a small model specialised for long tool-use chains may matter more than raw size for local agents, a trade-off the OSWorld gap makes visible. Builders running agents on local hardware can use it as a drop-in for multi-tool MCP workflows without cloud dependency. Compared with Qwen3.6-27B, it wins on tool orchestration but loses on general OS-level tasks.

#Muse Glimmer#Meta#open-source models#agents
Event
rohanpaul_ai@rohanpaul_aiSource
ModelsBuildersSelected13:20
Meta Publishes Technical Report on 30B Muse Glimmer Model

The notable part is the local deployment angle: a 30B agentic model that fits a single consumer GPU at 4-bit reduces dependence on cloud APIs and per-token costs. Developers building tool-use agents on local machines can study the distillation and quantization recipe for their own setups. It competes directly with similarly-sized open-weight models, so benchmark claims are worth verifying against your own workload.

#Muse Glimmer#Meta#open-source models#agents
Official accountMeta AI@AIatMetaSource