Llama 3
Open-weight LLM by Meta in 8B and 70B sizes with strong general capabilities.
About
Llama 3 is Meta's open-weight LLM family, originally released in 8B and 70B parameter instruct and base variants trained on 15 trillion tokens with an 8K context window. The models established the baseline that later Llama 3.1, 3.2, and 3.3 releases extended. This repository is the original minimal inference example and is now deprecated in favor of the consolidated llama-stack repos. Released under the Llama 3 Community License.
Reviews (0)
Leave a Review
No reviews yet. Be the first to review!
Details
- Category
- Large Language Models (LLMs)
- Price
- Free
- Platform
- Local/Desktop
- Difficulty
- Intermediate (3/5)
- License
- Llama 3 Community
- Minimum VRAM
- 8 GB
- Added
- Apr 3, 2026
Related Tools
Lightweight open-weight LLM by Google available in 1B to 27B sizes.
Open-source code LLM family by IBM for enterprise code generation.
High-performance open-weight MoE LLM with 671B total parameters.
Hybrid SSM-Transformer model by AI21 Labs combining Mamba with attention layers.
Family of small language models by Hugging Face for on-device use.
Open-weight code LLM trained on 2 trillion tokens of code and natural language.