Skip to content

Model family

Gemma local AI models

Explore the Gemma models currently tracked by AIPCFit. Compare parameter sizes, available model variants, catalog use cases, and hardware-fit guidance without treating model size as a universal performance guarantee.

5

Models

10

model variants

4B–27B

Parameter range

Google

Provider

Catalog use cases

chatcodingreasoninglightweightrag

Google

Gemma 3 27B

larger

27B parameters · 2 variants

chat · reasoning

Open model →1 GPU compatibility check

GPU compatibility links

GPU × model

Browse compatibility checks

See published dedicated-VRAM fit checks for selected NVIDIA RTX GPUs and local models.

Your hardware

What LLM can I run?

Start from your actual PC or Mac instead of a model family.