Back to llama
Meta /

Llama 4 Maverick 17B Instruct
Llama 4 Maverick 17B Instruct

Open WeightsMultimodaltextimageUpdated April 5, 2025
Some details or benchmark scores on this page are self-reported by developers and unconfirmed.

Llama 4 Maverick 17B Instruct

📌 Model Overview

Open multimodal Llama for strong reasoning with efficient everyday serving

Llama 4 Maverick 17B Instruct is a Open Weights model developed by Meta, released on 2025-04-05. It is designed primarily for Multimodal General workloads. Featuring a 1M tokens context window and 17B parameter count, it offers robust performance for enterprise integration, developers, and researchers.

✨ Key Features & Capabilities

Specification Table
FeatureDescription
Context Window1M tokens capacity for extended prompts and multi-turn workflows
Primary TaskOptimized for Multimodal General
Deploymentself-hostable, api-only
Modalitytext, image
Max OutputMax Output: 16K tokens
Tool / function calling supportTool / function calling support

⚙️ Technical Specifications

Specification Table
SpecificationDetails
Developer / LabMeta
Release Date2025-04-05
Model TypeOpen Weights
Parameters17B
Context Window1M tokens
LicenseLlama-3.3
Model Familyllama

📊 Benchmarks & Performance

Specification Table
BenchmarkScoreSource
Aider Polyglot15.6%Independent Eval
SWE-Bench Pro5.24 (resolve rate)Independent Eval

💰 Pricing

Specification Table
Tier / UnitRate (USD)
1M input tokens$0.27
1M output tokens$0.85

🔗 Resources & Links

Specification Table
ResourceLink
Hugging Facehttps://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E-Instruct

📜 License & Usage

This model is governed by the Llama-3.3 license. Please check official developer guidelines before commercial deployment.

Key Features

Max Output: 16K tokens

Feature 01✦

Tool / function calling support

Feature 02✦

You might also want to compare

Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-NEO-MAX-MTP-GGUF

DavidAU

Specs →

Inkling

Thinking Machines

Specs →

omni-moderation

OpenAI

Specs →

Verified Sources

Tags

tool-callingopen-weights

Model Specs

open-weights

Parameters

17B

Context Window

1M tokens

License

Llama-3.3

Deployment

self-hostableapi-only

Pricing

  • 1M input tokens$0.27
  • 1M output tokens$0.85

as of 2026-07-26

Resources & Links

Hugging Face

Lineage

Model Family

Part of the llama family

Llama 4 Scout 17B InstructLlama-3.3-70B-Instruct

Curator Notes

Skeleton entry imported from models.dev backfill (2026-07-26). Needs manual enrichment and primary-source verification.

Compare Specs

Compare parameters, context windows, modalities, and benchmark scores of this model side-by-side with others.

Compare Model