# Meta 发布 Muse Glimmer：30B 本地智能体模型

- 来源：Rohan Paul (@rohanpaul_ai)
- 发布时间：2026-08-10 19:00
- AIHOT 分数：52
- AIHOT 链接：https://aihot.virxact.com/items/cmsn4zb0i02enron5dosldyf2
- 原文链接：https://x.com/rohanpaul_ai/status/2086769766937837777

## AI 摘要

Meta Superintelligence Labs 发布 Muse Glimmer，一款 30B 参数、专为单消费级 GPU 上的常驻本地智能体设计的模型，权重以 Apache 2.0 协议开源。

## 正文

Meta Superintelligence Labs released Muse Glimmer, a 30B-parameter model built for always-on local agents on one consumer GPU.

weights on HuggingFace under an Apache 2.0 license,

• At full precision the model would need 55GB+ of memory.

• Meta compressed the weights to roughly 4-bit precision, shrinking the language model to under 20GB.
That leaves room inside a 24GB or 32GB envelope for the KV cache, a perception encoder for screenshots, and a speculative decoding drafter.

• The compressed model still leads Gemma4-31B and Qwen3.6-27B on MCP Atlas, at 75.5 against 54.2 and 62.5.

That lead reverses on computer use and terminal coding, where Qwen3.6-27B scores higher on OSWorld-Verified, TerminalBench 2.1, and SWE-Bench Verified.

• Instead of writing one word at a time, Muse Glimmer lets a small helper model called DFlash guess a whole block ahead.
The main model then checks that block in one pass, keeping the correct guesses and fixing the wrong ones.

• On an RTX-5090, that lifted decode speed from 74.9 to 233 tokens per second, a 3.1x gain measured through llama.cpp.

• Apple hardware gains less, 1.8x on an M5-Max and 1.5x on an M4-Max, reaching 50 and 38 tokens per second.

### 引用推文

> 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...