Fully open 3B language model with switchable reasoning mode, long context, tool calling and multilingual support, released with its training recipe.
google/gemma-3-270m-it
Indexed from Hugging FaceLinked to its home on Hugging Face. FrontierOS indexes it; nothing is hosted or mirrored here.ModelSmall language model270M paramsEst. Single-board computerEstimated minimum compute for inference: Raspberry Pi 5 class CPU. Not a benchmark.Gemma termsGatedGated upstream: accept the owner's terms on Hugging Face to download.Desk device
About
Tiny instruction-tuned Gemma 3 model meant to be fine-tuned for narrow jobs such as classification, extraction or command routing.
Why it matters for physical AI
A cheap starting point for task-specific device models that must run fast on minimal hardware.
Summary written by FrontierOS in our own words. The upstream card and license govern use. Metadata checked 27 Sep 2026. Read the full card on Hugging Face
Files, weights and version history live on Hugging Face. FrontierOS indexes this repo; it does not host or mirror it.
Gated upstream. Accept the owner's terms on Hugging Face and sign in with hf auth login before downloading.
hf download google/gemma-3-270m-itUses the Hugging Face CLI (pip install -U huggingface_hub). This downloads the whole repo; add --include "<pattern>" to fetch only the files you need.
More small language model
Browse allSmallest dense model in the Qwen3 family, with optional thinking mode and function-calling support.