Meta Llama 3 70B Instruct
Meta AI's Meta Llama 3 70B Instruct is a chat model optimized for dialogue use cases, with capabilities including function calling, JSON mode, reasoning, streaming, and text generation. It is genuinely best at handling a wide range of tasks due to its instruction tuning and large 70B parameter size.
Input
Output
Context
8K
Max Output
2K
Parameters
70.6B
Technical Specifications
Model TypeChat
Context Window8,192 tokens
Max Output Tokens2,048 tokens
Parameters70.6B
Release DateApr 17, 2024
Training CutoffDec 1, 2023
Licensellama3
Open SourceYes
Input Modalities
Text
Output Modalities
Text
Capabilities
Benchmarks
Artificial Analysis
4.4%
HLE
37.9%
GPQA
18.9%
SciCode
48.3%
MATH 500
57.4%
MMLU Pro
6.8
Coding
19.8%
LiveCodeBench
3.5
Intelligence
43.7
Speed (tok/s)
0.765
TTFA (s)
0.765
TTFT (s)
Resources & Links
Estimated GPU Requirements for Meta Llama 3 70B 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.