Llama3.1-8B

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

基础大模型

Llama3.1-8B

Release date: 2024-07-23更新于: 2024-07-24 00:03:32695

Live demo

Llama3.1-8B is an AI model published by Facebook AI研究实验室, released on 2024-07-23, for 基础大模型, 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

基础大模型

Release date

2024-07-23

Model file size

16GB

MoE architecture

Total params / Active params

80.0B / N/A

Knowledge cutoff

No data

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.