llama-3.3-70b-instruct-awq
- Task
- Text generation
- Category
- Language
- License
- llama3.3
- Commercial use
- Yes, with conditions
The publisher's own model license: commercial use is allowed under its terms, which include limits; read them before shipping. - Size
- About 70 billion parameters
- Memory to load
- ~42 GB (estimate)
- Format
- AWQ
- Runs on
- GPU
- Access
- Open download
- Downloads (last 30 days)
- 767K
- Likes
- 53
- Last updated
- December 6, 2024
How to run it
These are 4-bit quantized weights for NVIDIA GPUs; load them with a library that supports AWQ, such as vLLM or Hugging Face Transformers.
Plan for roughly 42 GB of memory to load it (our estimate from its size and format).
The model card on Hugging Face has the exact usage code.
Related text generation models
Data from Hugging Face's public API, last checked October 19, 2026. Downloads are Hugging Face's count for the last 30 days.