Run SmolLM2 1.7B Instruct in your browser
SmolLM2 1.7B Instruct is a 1.7B Hugging Face model. In the browser it downloads 918 MB and needs about 1.7 GB of GPU memory.
Use SmolLM2 1.7B Instruct in the browser All models Downloads once · then works offline
- Family
- SmolLM
- Published by
- Hugging Face
- Parameters
- 1.7B
- Quantisation
- q4f16_1 · 4-bit
- Download
- 918 MB · 37 files
- GPU memory
- 1.7 GB
- Context window
- 4k tokens
- Reasoning
- —
- Licence
- Apache 2.0
- Base model
- HuggingFaceTB/SmolLM2-1.7B-Instruct
- Good at
- Chat
How big is the SmolLM2 1.7B Instruct download?
918 MB for the q4f16_1 build, in 37 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 1.7B Instruct?
A browser with WebGPU — recent Chrome, Edge, Firefox or Safari — and about 1.7 GB of GPU memory. The tool checks your GPU, memory and free space and tells you whether SmolLM2 1.7B Instruct fits before anything downloads.
Is anything I type sent to a server?
No. SmolLM2 1.7B Instruct 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 1.7B Instruct 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 1.7B Instruct 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 SmolLM2 1.7B Instruct released under?
The weights are Apache 2.0, taken from the model card of HuggingFaceTB/SmolLM2-1.7B-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.
