Llama 4 Maverick 17B 128E Instruct
Llama 4 Maverick 17B 128E Instruct is a 17 billion parameter language model from Meta, part of Meta's open-weight Llama family. It features accepts image inputs alongside text. It is released under the other license.
Input
Output
Context
131K
Max Output
8K
Parameters
17B
Technical Specifications
Model TypeChat
Context Window131K
Max Output Tokens8K
Parameters17B
Training Cutoff—
Licenseother
Capabilities
Input Modalities
textimage
Output Modalities
text
Features
function_callingjson_modereasoningstreamingtext_generationvision
Benchmarks
#86
Rank (Text)
+4/-4
arena text ci 95
1292
Arena Score (Text)
24,544
Votes (Text)
#39
Rank (Vision)
+10/-10
arena vision ci 95
1184
Arena Score (Vision)
4,857
Votes (Vision)
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: May 5, 2026
Start building with the right model.
From model selection to production, one platform, no fragmentation.