Llama 4 Maverick 17B 128E Instruct
Llama 4 Maverick 17B 128E Instruct FP 8 is a chat model developed by Meta AI, leveraging a mixture-of-experts architecture to enable text and multimodal experiences, including text and image understanding. It is genuinely best at handling a wide range of inputs, including text and images, and supporting multiple languages, with a notable technical trait being its large context window of 1,000,000 tokens.
Input
Output
Context
1000K
Max Output
16K
Parameters
401.6B
Technical Specifications
Model TypeChat
Context Window1,000,000 tokens
Max Output Tokens16,384 tokens
Parameters401.6B
Release DateApr 1, 2025
Training CutoffAug 1, 2024
Licenseother
Open SourceYes
Input Modalities
TextImage
Output Modalities
Text
Capabilities
Benchmarks
Artificial Analysis
4.8%
HLE
39.0%
AIME
67.1%
GPQA
33.1%
SciCode
88.9%
MATH 500
80.9%
MMLU Pro
19.3
Math
15.6
Coding
39.7%
LiveCodeBench
14.3
Intelligence
96.4
Speed (tok/s)
0.633
TTFA (s)
0.633
TTFT (s)
Resources & Links
Estimated GPU Requirements for Llama 4 Maverick 17B 128E Instruct
Estimates based on INT8 quantization. Actual requirements vary by framework and configuration.
Related Tools
Data sourced from official provider APIs and documentation
Last updated: Jun 24, 2026
Start building with the right model.
Automatically route workloads to the right model for every task, every time.