Meta: Llama 3.3 70B Instruct (free)

Meta

The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out). The Llama 3.3 instruction tuned text only model is optimized for multilingual dialogue use cases and outperforms many of the available open source and closed chat models on common industry benchmarks. Supported languages: English, German, French, Italian, Portuguese, Hindi, Spanish, and Thai. [Model Card](https://github.com/meta-llama/llama-models/blob/main/models/llama3_3/MODEL_CARD.md)

Other versions in the Llama family

Llama Guard 3 8B

8B

Meta: Llama 3 70B Instruct

70B

Meta: Llama 3 8B Instruct

8B

Meta: Llama 3.1 70B Instruct

70B

Meta: Llama 3.1 8B Instruct

8B