Llama 3.2 3B
Stronger than the 1B (~2.2 GB VRAM). Still WebLLM low-resource.
- Runs on
- Your device, in the browser
- Size
- 3B
- Best for
- Everyday chat
Llama 3.2 3B runs in your browser, on your own device. The model downloads once and stays there; what you type is never sent to Meta or to us , and no API key is involved.
Context window
131,072 tokens
≈ 98,000 words · about 390 pages
the model's own limit — how much your device can hold depends on its memory
Knowledge cutoff
December 2023
its training cutoff
Modalities
- TextInput and output
- ImageNot supported
- AudioNot supported
- VideoNot supported
Features
- StreamingSupported
- Function callingNot supported
- Structured outputsSupported
- Fine-tuningNot supported
Where it comes from
| Model card | Meta's card for Llama 3.2 3B |
|---|---|
| Weights | The build your browser downloads |
| Runtime | WebLLM |
Ready to try it?
Polymeti is currently invite-only.
Log inRuns on your device · No API key · Your chats stay in your browser