DataLearner logoDataLearnerAI
Latest AI Insights
Model Evaluations
Model Directory
Model Comparison
Resource Center
Tool Directory

加载中...

DataLearner logoDataLearner AI

A knowledge platform focused on LLM benchmarking, datasets, and practical instruction with continuously updated capability maps.

产品

  • Leaderboards
  • 模型对比
  • Datasets

资源

  • Tutorials
  • Editorial
  • Tool directory

关于

  • 关于我们
  • 隐私政策
  • 数据收集方法
  • 联系我们

© 2026 DataLearner AI. DataLearner curates industry data and case studies so researchers, enterprises, and developers can rely on trustworthy intelligence.

隐私政策服务条款
Page navigation
目录
Model catalogLlama 4 Maverick Instruct
LL

Llama 4 Maverick Instruct

Llama-4-Maverick-17B-128E-Instruct

Release date: 2025-04-05更新于: 2025-04-15 16:27:15750
Live demoGitHubHugging FaceCompare
Parameters
4000.0亿
Context length
1000K
Chinese support
Supported
Reasoning ability

Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology

Llama 4 Maverick Instruct

Model basics

Reasoning traces
Not supported
Context length
1000K tokens
Max output length
4096 tokens
Model type
多模态大模型
Release date
2025-04-05
Model file size
218GB
MoE architecture
No
Total params / Active params
4000.0B / N/A
Knowledge cutoff
No data
Inference modes
No mode data
Llama 4 Maverick Instruct

Open source & experience

Code license
Llama4 License
Weights license
Llama4 License- 免费商用授权
GitHub repo
https://github.com/meta-llama/llama-models/tree/main/models/llama4
Hugging Face
https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E
Live demo
No live demo
Llama 4 Maverick Instruct

Official resources

Paper
The Llama 4 herd: The beginning of a new era of natively multimodal AI innovation
DataLearnerAI blog
No blog post yet
Llama 4 Maverick Instruct

API details

API speed
4/5
No public API pricing yet.
Llama 4 Maverick Instruct

Benchmark Results

综合评估

2 evaluations
Benchmark / mode
Score
Rank/total
MMLU ProNormal
80.50
43 / 112
GPQA DiamondNormal
69.80
90 / 153

编程与软件工程

1 evaluations
Benchmark / mode
Score
Rank/total
LiveCodeBenchNormal
43.40
80 / 103
查看评测深度分析与其他模型对比
Llama 4 Maverick Instruct

Publisher

Facebook AI研究实验室
Facebook AI研究实验室
View publisher details
Llama-4-Maverick-17B-128E-Instruct

Model Overview

Llama 4 Maverick是MetaAI开源的一款基于MoE架构的大模型。该模型拥有170亿活跃参数，并配备了128个专家单元，总参数量达到4000亿，其设计旨在通过专家路由机制提升模型在多模态任务中的性能，同时保持较高的计算效率。


Llama 4 Maverick Instruct是其中指令微调的版本，全称是Llama-4-Maverick-17B-128E-Instruct，其中128E就是128个专家。这个模型与另一个Llama4模型，即Llama 4 Scout架构一样，只是专家数量不同，进而总的参数量也不一样，效果也更好。

DataLearner 官方微信

欢迎关注 DataLearner 官方微信，获得最新 AI 技术推送

DataLearner 官方微信二维码