Skip to content

Meta Llama 3 8B

meta-llama/Meta-Llama-3-8B
Open Source · chat · open-weights
GA Alert me on changes
Context
8.2K
Max output
Input $/1M
$0.05
Output $/1M
$0.08
Modalities
text
Released
17 Apr 2024
License: llama3 · meta-llama/Meta-Llama-3-8B
AI summary
● machine-written

Meta Llama 3 8B open-weights text model released April 2024

Meta Llama 3 8B is an 8-billion parameter open-weights model designed for text generation tasks. Released April 17, 2024, it is available under the Llama 3 license and can be deployed locally or via inference providers. The model serves as a lightweight alternative in the Llama 3 family for applications requiring efficient inference.

What's new
  • Open-weights model available on Hugging Face with 1.2M+ downloads
  • Llama 3 license enables commercial use with acceptance policy compliance
  • Supports multiple deployment frameworks (Transformers, vLLM, SGLang)
  • Evaluated on MMLU-Pro benchmark (35.36% score)
Best for
Local deployment and edge inferenceText generation applicationsFine-tuning and custom implementationsCost-sensitive production workloads
Sources

Source: https://huggingface.co/meta-llama/Meta-Llama-3-8B