跳轉到主要內容

Muse Glimmer-30B

Meta開源權重Apache 2.0 · 商用許可

描述

Muse Glimmer-30B is Meta Superintelligence Labs' open-weight, dense multimodal model for autonomous agentic work on consumer hardware. Its 29.6-billion-parameter causal transformer includes a roughly 1.8B-parameter ViT-G/14 perception encoder, accepts interleaved text and images, produces text, and supports a 131,072-token context window. It combines controllable multi-step reasoning, schema-based tool use, coding, failure recovery, and compatibility with agent scaffolds such as OpenClaw and Hermes Agent. Meta also releases 4-bit variants sized for 24 GB and 32 GB systems and a DFlash speculative-decoding drafter. The model is trained on more than 100 languages and released under Apache 2.0.

發布日期
2026-08-10
參數規模
29.6B
上下文長度
131K
支援模態
image, text

能力雷達圖

37
general
60
coding
60
reasoning
51
science估算
70
agents
70
multimodal

缺少專門科學評測時,Science 由 LLM Stats 科學得分或推理能力估算。

排行榜排名

領域#排名分數來源
智慧體能力模型榜104
41.0
LS
多模態榜89
47.0
LS

基準測試分數 (LLM Stats)

(LLM Stats (zeroeval))

Agents

Siren AgentDojo Utility94.2%自報
CI Memories Coverage64.8%自報
WildClawBench47.6%自報
Siren AgentDojo Attack Success Rate28.4%自報
CI Memories Violation Rate26.4%自報
Tau3 Banking23.5%自報

Chat

Tau2 Airline78.0%自報

Code

PinchBench90.5%自報
SkillsBench44.3%自報

Communication

Tau2 Telecom94.1%自報
Tau2 Retail87.1%自報

General

GDPval-AA953.00 / 3000自報
GAIA243.3%自報

Instruction Following

IFBench77.0%自報

Language

MMLU-ProX80.1%自報

Math

AIME 202694.7%自報

Multimodal

OSWorld-Verified65.9%自報

Reasoning

GPQANYU + Cohere + Anthropic (2023)83.5%自報
AA-LCR80.0%自報
CharXiv-R78.8%自報
SWE-Bench Verified76.0%自報
MCP Atlas75.5%自報
ARC-AGI66.9%自報
Beam 128K65.1%自報
Terminal-Bench 2.151.7%自報
SWE-Bench ProPrinceton NLP (2024)51.2%自報
SciCode43.6%自報
Humanity's Last Exam22.0%自報

Search

DeepSearchQA74.6%自報

Vision

OmniDocBench 1.575.8%自報
ScreenSpot Pro75.4%自報
MMMU-Pro74.0%自報

AA 評測指數

(Artificial Analysis)

暫無 AA 評測資料

LLM Stats 分類評分

(LLM Stats (zeroeval))
Legal
100
Finance
100
Agents
96
Reasoning
48
General
37
Communication
90
Chat
80
Instruction Following
80
Language
80
Long Context
80
Structured Output
80
Frontend Development
80
Grounding
80
Healthcare
80
Multimodal
70
Search
70
Spatial Reasoning
70
Tool Calling
70
Vision
70
Math
60
Physics
60
Biology
60
Chemistry
60
Code
60
Coding
50

定價

輸入價格$0.3 / 1M tokens
輸出價格$1.2 / 1M tokens
混合價格(3:1)$0.525 / 1M tokens
快取讀取價格$0.04 / 1M tokens

速度

暫無速度資料

供應商價格排行

供應商價格排行

10 個供應商

最便宜: DeepInfra最貴: AI/ML API
供應商輸入輸出
1DeepInfra最便宜
$0
$0
2EmpirioLabs AI
$0.2
$0.8
3Vultr
$0.25
$1
4Meta主要
$0.3
$1.2
5OpenRouter
$0.3
$1.2
6Kilo Gateway
$0.3
$1.2
7DevPass (LLM Gateway)
$0.3
$1.2
8NanoGPT
$0.35
$1.5
9Vercel AI Gateway
$0.35
$1.5
10AI/ML API
$0.3703
$1.587

比較該模型在不同 API 供應商之間的定價。

外部連結