SmolLM · 3B · Desktop / import

SmolLM3 3B on a phone

Hugging Face’s 2025 small model — a step up from SmolLM2, still phone-sized.

Parameters
3B
Typical Q4
~1.9 GB (Q4)
RAM to budget
~3.3 GB
Engines
GGUF

Get it running

HuggingFaceTB/SmolLM3-3B. GGUF via bartowski / community. Hugging Face: HuggingFaceTB/SmolLM3-3B.

Load in LM Studio or Ollama, then chat from the phone.

Get LM Mini and load a model that actually fits — on-device, or via Connect to a PC.

Phones that can run it

Tight (close other apps)

  • None in this guide — use a Mac or Connect.