SmolLM2

SmolLM2 is a compact large language model (LLM) developed by Hugging Face.
It is designed for efficient natural language tasks such as text generation,
summarization, and question answering.

Use this snap to quickly install an optimized environment for local inference with SmolLM2.

The snap includes the following hardware-optimized inference engines:

• cpu: Optimized for x64 and ARM (armv8, armv9) CPUs
• nvidia-gpu: CUDA-enabled GPU acceleration

The most suitable engine is automatically selected based on the available hardware.

Install:

sudo snap install smollm2

Run:

smollm2

Some accelerators require extra drivers to be usable with this snap: https://documentation.ubuntu.com/inference-snaps/how-to/setup/drivers/

License:

The SmolLM2 model is provided by Hugging Face under the Apache 2.0 license: https://huggingface.co/collections/HuggingFaceTB/smollm2

The licenses of all the bundled software can be found after installing the snap at /snap/smollm2/current/usr/share/doc.