Skip to content
localmodel.run

Text model · gemma

Gemma 3 1B requirements

gemma family · 1B params · released 2025-03-12 · 32.8M Ollama pulls. Minimum to run at Q4_K_M: Apple M1 (8GB).

LicenseGemma· Conditional↓ 1.5M/mo♥ 1Kon HuggingFace
Q4_K_M
0.81 GB
Q8_0
1.07 GB
Total @ Q4 (4k)
~1.8 GB
Context
32 k

Quantization sizes

GGUF quantson disk
QuantizationSize on disk
Q2_K0.4 GB est
Q3_K_M0.5 GB est
Q4_K_M (default)0.81 GB
Q5_K_M0.7 GB est
Q6_K0.8 GB est
Q8_01.07 GB
FP162 GB est

Lower quant = smaller and faster, slightly lower quality. Q4_K_M is the common default.

Run it

Ollama
$ ollama run gemma3:1b
llama.cpp
$ llama-cli -hf bartowski/google_gemma-3-1b-it-GGUF:Q4_K_M
LM Studio
$ lms get bartowski/google_gemma-3-1b-it-GGUF

Which devices can run Gemma 3 1B?

FAQ

How much VRAM or RAM does Gemma 3 1B need?

At Q4_K_M, Gemma 3 1B needs about 1.8 GB (weights ~0.81 GB + KV cache + overhead) at a 4k context. At Q8_0 budget ~2.1 GB.

Can Gemma 3 1B run on a laptop?

Yes, Gemma 3 1B fits on a 16 GB machine at Q4_K_M and runs on Apple Silicon or a 12 GB+ GPU comfortably.

Can I use Gemma 3 1B commercially?

Conditionally. Gemma Terms of Use apply to commercial use.

Google's ultra-small Gemma 3 model. 32K context, multilingual support, strong reasoning for 1B scale. Designed to run on a single GPU or phone-class hardware.

Sources

Memory figures are estimates. See methodology.