LL

Llama3-70B

Chat modelLlama3

Llama3-70B

Release date: 2024-04-18Updated: 2024-04-19 00:29:13761
Parameters
70B
Context length
8K
Chinese support
Not supported
Reasoning ability

Llama3-70B is an AI model published by Facebook AI研究实验室, released on 2024-04-18, for Chat model, with 70B parameters, and 8K context length, requiring about 140GB storage, under the Llama 2 Community License Agreement license, with a 52.78 score on MMLU Pro.

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

Llama3-70B

Model basics

Reasoning traces
Not supported
Thinking modes
Thinking modes not supported
Context length
8K tokens
Max output length
No data
Model type
Chat model
Modality (in / out)
No data
Release date
2024-04-18
Model file size
140GB
MoE architecture
No
Total params / Active params
70B / N/A
Knowledge cutoff
No data
Llama3-70B

Open source & experience

Llama3-70B

Official resources

Llama3-70B

API details

API speed
No data
No public API pricing yet.
Llama3-70B

Benchmark Results

Llama3-70B currently shows benchmark results led by MMLU Pro (114 / 126, score 52.78). This page also consolidates core specs, context limits, and API pricing so you can evaluate the model from benchmark results and deployment constraints together.

Thinking

General Knowledge

1 evaluations
Benchmark / mode
Score
Rank/total
52.78
114 / 126

Compare with other models

No curated comparisons for this model yet.

Want a custom combination? Open the compare tool

Llama3-70B

Publisher

Facebook AI研究实验室
View publisher details
Llama3-70B

Model Overview

Llama3-70B is an AI model published by Facebook AI研究实验室, released on 2024-04-18, for Chat model, with 70B parameters, and 8K context length, requiring about 140GB storage, under the Llama 2 Community License Agreement license, with a 52.78 score on MMLU Pro.

DataLearner on WeChat

Follow DataLearner on WeChat for AI model updates and research notes.

DataLearner WeChat QR code