Llama 3.1 405B

Summary: Large US model with high response quality but slow inference speed introduced by Meta.

Intelligence

Speed

Sovereignty

Input

Output

High

Low

Low

Text

Text

Central parameters

Description: Meta Llama 3.1 405B is the largest pure open-source large language model trained by Meta. It is especially suited for use cases with irrelevant response time, but crucial answer quality. It natively supports various European languages but focuses on English.

Model identifier: meta-llama/Meta-Llama-3.1-405B-Instruct-FP8

IONOS AI Model Hub Lifecycle and Alternatives

IONOS Launch

End of Life

Alternative

Successor

August 1, 2024

N/A

Origin

Provider

Country

License

Flavor

Release

USA

Instruct

July 23, 2024

Technology

Context window

Parameters

Quantization

Multilingual

128k

406B

int4

Yes

Modalities

Text

Image

Audio

Input and output

Not supported

Not supported

Endpoints

Chat Completions

Embeddings

Image generation

v1/chat/completions

Not supported

Not supported

Features

Streaming

Tool calling

Supported

Supported

Rate limits

Rate limits ensure fair usage and reliable access to the AI Model Hub. In addition to the contract-wide rate limits, no model-specific limits apply.

Last updated

Was this helpful?