Llama 3.2 3B Instruct
Developed by Meta AI, Llama 3.2 3B Instruct is a multilingual large language model optimized for dialogue use cases, including agentic retrieval and summarization tasks, with capabilities such as function calling, JSON mode, and text generation. It utilizes an optimized transformer architecture with supervised fine-tuning and reinforcement learning with human feedback.
Input
Output
Context
131K
Max Output
-
Parameters
3.2B
Technical Specifications
Model TypeChat
Context Window131,072 tokens
Max Output TokensNot available
Parameters3.2B
Release DateSep 18, 2024
Training CutoffDec 1, 2023
Licensellama3.2
Open SourceYes
Input Modalities
Text
Output Modalities
Text
Capabilities
Benchmarks
Artificial Analysis
5.2%
HLE
6.7%
AIME
25.5%
GPQA
5.2%
SciCode
48.9%
MATH 500
34.7%
MMLU Pro
3.3
Math
8.3%
LiveCodeBench
4.2
Intelligence
52.0
Speed (tok/s)
0.600
TTFA (s)
0.600
TTFT (s)
Resources & Links
Estimated GPU Requirements for Llama 3.2 3B 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.