Run Llama 3.2 1B in your browser
Meta’s small instruct model. Low memory use and dependable for everyday questions.
Use Llama 3.2 1B in the browser All models Downloads once · then works offline
- Family
- Llama
- Published by
- Meta
- Parameters
- 1B
- Quantisation
- q4f16_1 · 4-bit
- Download
- 663 MB · 22 files
- GPU memory
- 879 MB
- Context window
- 4k tokens
- Reasoning
- —
- Licence
- Llama 3.2 Community License
- Base model
- meta-llama/Llama-3.2-1B-Instruct
- Good at
- Chat · Multilingual
How big is the Llama 3.2 1B download?
663 MB for the q4f16_1 build, in 22 files. It downloads once and stays in your browser cache, so every later visit starts straight away and works offline.
What does my device need to run Llama 3.2 1B?
A browser with WebGPU — recent Chrome, Edge, Firefox or Safari — and about 879 MB of GPU memory. The tool checks your GPU, memory and free space and tells you whether Llama 3.2 1B fits before anything downloads.
Is anything I type sent to a server?
No. Llama 3.2 1B runs on your own GPU inside the browser tab. The only network traffic is the one-time download of the model files from Hugging Face; your prompts and the answers never leave the device, and the chats are stored in this browser.
Which build of Llama 3.2 1B should I choose?
Start with q4f16_1 — it is the smallest download and the fastest to run. The f32 builds are larger and use more memory, but they run on GPUs without 16-bit shader support. Builds marked 1k hold a shorter conversation in exchange for less memory.
How long a conversation can Llama 3.2 1B hold?
Its context window is 4k tokens. Longer conversations keep working — the oldest turns are dropped with a notice when the conversation no longer fits.
What licence is Llama 3.2 1B released under?
The weights are Llama 3.2 Community License, taken from the model card of meta-llama/Llama-3.2-1B-Instruct. Check the licence yourself before using it commercially.
Figures read from the WebLLM 0.2.84 catalog and the model card on 2026-09-03.
