LL

Llama 4 Maverick Instruct

Multimodal modelLlama 4

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

Release date: 2025-04-05Updated: 2025-04-15 16:27:15916
Parameters
400B
Context length
1000K
Chinese support
Supported
Reasoning ability

Llama-4-Maverick-17B-128E-Instruct is an AI model published by Facebook AI研究实验室, released on 2025-04-05, for Multimodal model, with 400B parameters, and 1000K context length, requiring about 218GB storage, under the Llama4 License license, with a 80.50 score on MMLU Pro.

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
Thinking modes
Thinking modes not supported
Context length
1000K tokens
Max output length
4K tokens
Model type
Multimodal model
Modality (in / out)
Text, Image, Audio, Video → Text
Release date
2025-04-05
Model file size
218GB
MoE architecture
No
Total params / Active params
400B / N/A
Knowledge cutoff
No data
Llama 4 Maverick Instruct

Open source & experience

Llama 4 Maverick Instruct

Official resources

Llama 4 Maverick Instruct

API details

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

Benchmark Results

Llama 4 Maverick Instruct currently shows benchmark results led by MMLU Pro (57 / 126, score 80.50), GPQA Diamond (116 / 179, score 69.80), LiveCodeBench (96 / 120, score 43.40). This page also consolidates core specs, context limits, and API pricing so you can evaluate the model from benchmark results and deployment constraints together.

Thinking

General Knowledge

2 evaluations
Benchmark / mode
Score
Rank/total
80.50
57 / 126
69.80
116 / 179

Coding and Software Engineer

1 evaluations
Benchmark / mode
Score
Rank/total
43.40
96 / 120

Compare with other models

No curated comparisons for this model yet.

Want a custom combination? Open the compare tool

Llama 4 Maverick Instruct

Publisher

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

Model Overview

Llama-4-Maverick-17B-128E-Instruct is an AI model published by Facebook AI研究实验室, released on 2025-04-05, for Multimodal model, with 400B parameters, and 1000K context length, requiring about 218GB storage, under the Llama4 License license, with a 80.50 score on MMLU Pro.

DataLearner on WeChat

Follow DataLearner on WeChat for AI model updates and research notes.

DataLearner WeChat QR code