Llama3.1-8B

Name: Llama3.1-8B
Author: Facebook AI研究实验室

Foundation model

Llama3.1-8B

Release date: 2024-07-23Updated: 2024-07-24 00:03:32709

Live demoGitHub Hugging Face Compare

Parameters

Context length

128K

Chinese support

Not supported

Reasoning ability

Llama3.1-8B is an AI model published by Facebook AI研究实验室, released on 2024-07-23, for Foundation model, with 80.0B parameters, and 128K tokens context length, requiring about 16GB storage, under the LLAMA 3.1 COMMUNITY LICENSE AGREEMENT license.

Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology

Llama3.1-8B

Model basics

Reasoning traces

Not supported

Thinking modes

Thinking modes not supported

Context length

128K tokens

Max output length

No data

Model type

Foundation model

Release date

2024-07-23

Model file size

16GB

MoE architecture

Total params / Active params

8B / N/A

Knowledge cutoff

No data

Llama3.1-8B

Open source & experience

Code license

LLAMA 3.1 COMMUNITY LICENSE AGREEMENT

Weights license

LLAMA 3.1 COMMUNITY LICENSE AGREEMENT- 免费商用授权

GitHub repo

https://github.com/meta-llama/llama-models/tree/main/models/llama3_1

Hugging Face

https://huggingface.co/meta-llama/Meta-Llama-3.1-8B

Live demo

No live demo

Llama3.1-8B

Official resources

Paper

No paper available

DataLearnerAI blog

Llama3.1-8B

API details

API speed

No data

No public API pricing yet.

Llama3.1-8B

Benchmark Results

Llama3.1-8B currently shows benchmark results led by BBH (15 / 20, score 57.70), GSM8K (21 / 26, score 55.30), MBPP (25 / 28, score 53.90). This page also consolidates core specs, context limits, and API pricing so you can evaluate the model from benchmark results and deployment constraints together.