gemma
1B parameters
Commercial OK

Gemma 3 1B

Smallest text-only Gemma 3 for phones and IoT.

License: Gemma Terms of Use·Released Mar 12, 2025·Context: 32,768 tokens

Overview

Smallest text-only Gemma 3 for phones and IoT.

Strengths

  • Phone-class
  • Text-only fast inference

Weaknesses

  • No vision
  • Limited reasoning

Quantization variants

Each quantization trades model quality for file size and VRAM. Q4_K_M is the most popular starting point.

QuantizationFile sizeVRAM required
Q4_K_M0.7 GB2 GB

Get the model

Ollama

One-line install

ollama run gemma3:1bRead our Ollama review →

HuggingFace

Original weights

huggingface.co/google/gemma-3-1b-it

Source repository — direct quantization required.

Hardware that runs this

Cards with enough VRAM for at least one quantization of Gemma 3 1B.

Compare alternatives

Models worth comparing

Same parameter band, plus what's one tier above and below — so you can decide what actually fits your hardware.

Same tier
Models in the same parameter band as this one
Step up
More capable — bigger memory footprint
Step down
Smaller — faster, runs on weaker hardware
No verdicted models in the next tier down yet.

Frequently asked

What's the minimum VRAM to run Gemma 3 1B?

2GB of VRAM is enough to run Gemma 3 1B at the Q4_K_M quantization (file size 0.7 GB). Higher-quality quantizations need more.

Can I use Gemma 3 1B commercially?

Yes — Gemma 3 1B ships under the Gemma Terms of Use, which permits commercial use. Always read the license text before deployment.

What's the context length of Gemma 3 1B?

Gemma 3 1B supports a context window of 32,768 tokens (about 33K).

How do I install Gemma 3 1B with Ollama?

Run `ollama pull gemma3:1b` to download, then `ollama run gemma3:1b` to start a chat session. The default quantization is Q4_K_M.

Source: huggingface.co/google/gemma-3-1b-it

Reviewed by RunLocalAI Editorial. See our editorial policy for how we research and verify model claims.