NewJoin us for the Forge keynote livestream on November 3rd
DocsLog inGet started
Meta logo

Llama 4 Maverick Instruct (Basic)

Ready
model path:accounts/fireworks/models/llama4-maverick-instruct-basic
Deploy on demand

The Llama 4 collection of models are natively multimodal AI models that enable text and multimodal experiences. These models leverage a mixture-of-experts architecture to offer industry-leading performance in text and image understanding.

Llama 4 Maverick Instruct (Basic) API Features

On-demand Deployment

Docs

On-demand deployments allow you to use Llama 4 Maverick Instruct (Basic) on dedicated GPUs with Fireworks' high-performance serving stack with high reliability and no rate limits.

Metadata

State
Ready
Created on
5 APR, 2025
Kind
Base model
Provider
Meta
Huggingface
meta-llama/Llama-4-Maverick-17B-128E-Instruct

Specifications

Calibrated
Yes
Mixture-of-Experts
Yes
Parameters
401B

Supporting Functionality

Fine-tuning
Not Supported
Serverless
Not Supported
Context Length
1040k tokens
Function Calling
Supported
Embeddings
Not Supported
Rerankers
Not Supported
Supporting image input
Supported

Llama 4 Maverick Instruct FAQs

Llama 4 Maverick Instruct is the instruction-tuned variant of Llama 4 Maverick, a 17 billion-parameter mixture-of-experts (128 experts, 400B total parameters) multimodal model created by Meta.