Run SmolLM2 360M in your browser
The lightest chat model here. Answers instantly on almost any GPU; keep questions simple.
Use SmolLM2 360M in the browser All models Downloads once · then works offline
- Family
- SmolLM
- Published by
- Hugging Face
- Parameters
- 360M
- Quantisation
- q4f16_1 · 4-bit
- Download
- 194 MB · 7 files
- GPU memory
- 376 MB
- Context window
- 4k tokens
- Reasoning
- —
- Licence
- Apache 2.0
- Base model
- HuggingFaceTB/SmolLM2-360M-Instruct
- Good at
- Chat
How big is the SmolLM2 360M download?
194 MB for the q4f16_1 build, in 7 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 SmolLM2 360M?
A browser with WebGPU (a recent Chrome, Edge, Firefox or Safari) and about 376 MB of GPU memory. Before anything downloads, the tool checks your GPU, memory and free space and tells you whether SmolLM2 360M fits.
Is anything I type sent to a server?
No. SmolLM2 360M 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 SmolLM2 360M 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 SmolLM2 360M hold?
Its context window is 4k tokens. Longer conversations still work: once the conversation no longer fits, the oldest turns are dropped and you see a notice.
What licence is SmolLM2 360M released under?
The weights are Apache 2.0, taken from the model card of HuggingFaceTB/SmolLM2-360M-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.
