Gemma

Gemma model size lanes for local AI decisions.

1 model sizes 4B 8 GB

Gemma model sizes

Compare Gemma rows by task, VRAM band, and context before opening a size page.

1 sizes1 family

Memory fit

View

Tasks

Sort

1 of 1 model sizesall tasksAll VRAM

Gemma 3 4B

Google · 4B

8 GB

A compact image-and-text instruction model for local assistant experiments.

Limitation: Its 128K capability is not a promise that a 128K workload fits a particular machine; validate runtime, quantization, and context overhead.

Source: Primary model source · Official model card checked 2026-08-06

Official Google model card; Gemma terms require agreement.

VRAM bands are planning estimates for local fit exploration. Validate context length and sustained performance before making a hardware decision.