Skip to content
localmodel.run

Text model · gemma

Gemma 2 2B requirements

gemma family · 2.61B params · released 2024-07-31 · 17.2M Ollama pulls. Minimum to run at Q4_K_M: Apple M1 (8GB).

LicenseGemma· Conditional↓ 228.7K/mo♥ 1.4Kon HuggingFace
Q4_K_M
1.71 GB
Q8_0
2.78 GB
Total @ Q4 (4k)
~2.9 GB
Context
8 k

Quantization sizes

GGUF quantson disk
QuantizationSize on disk
Q2_K1.1 GB est
Q3_K_M1.3 GB est
Q4_K_M (default)1.71 GB
Q5_K_M1.9 GB est
Q6_K2.1 GB est
Q8_02.78 GB
FP165.2 GB est

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

Run it

Ollama
$ ollama run gemma2:2b
llama.cpp
$ llama-cli -hf bartowski/gemma-2-2b-it-GGUF:Q4_K_M
LM Studio
$ lms get bartowski/gemma-2-2b-it-GGUF

Which devices can run Gemma 2 2B?

FAQ

How much VRAM or RAM does Gemma 2 2B need?

At Q4_K_M, Gemma 2 2B needs about 2.9 GB (weights ~1.71 GB + KV cache + overhead) at a 4k context. At Q8_0 budget ~4 GB.

Can Gemma 2 2B run on a laptop?

Yes, Gemma 2 2B 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 2 2B commercially?

Conditionally. Gemma Terms of Use apply to commercial use.

Google's smallest Gemma 2 model. Uses sliding-window attention (local 4K + global 8K). Strong code and reasoning for its size. Released July 31, 2024 separately from the 9B/27B launch.

Sources

Memory figures are estimates. See methodology.