by openai-community
⬇ 29.8M♥ 3.9K
Llama-3.2-3B-Instruct-4bit-Lantern
- Task
- Text generation
- Category
- Language
- License
- Llama 3.2 license
- 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 3 billion parameters
- Memory to load
- ~2 GB (estimate)
- Format
- MLX
- Runs on
- CPU
- Access
- Open download
- Downloads (last 30 days)
- 0
- Likes
- 0
- Last updated
- September 28, 2026
How to run it
This is an MLX build for Apple silicon Macs; run it with Apple's MLX framework (mlx-lm for language models).
Plan for roughly 2 GB of memory to load it (our estimate from its size and format).
The model card on Hugging Face has the exact usage code.
Where to run it
On your own computer, free
Both load GGUF builds; for other formats, look for a GGUF version of this model.
In the cloud
Needs about 2 GB: a 24 GB GPU such as an RTX 4090 or RTX A5000 is enough.
- RunPod · rent a GPU by the hour (affiliate link)
Related text generation models
Data from Hugging Face's public API, last checked September 28, 2026. Downloads are Hugging Face's count for the last 30 days.