Gemma 4.

A calm, image-literate lineup for turning what is on the screen into useful language—captioning, explaining, comparing, and drafting without an upload step.

View on Hugging Face See LocalEngine variants ↓

Model makerGoogle

Supported in LocalEnginemacOS + iPhone & iPad

Upstream licenseGemma terms

SourceGemma 4 collection ↗

Where it earns its space

Built for a real local rhythm.

These are good-fit starting points—not promises of benchmark performance. Choose the smallest listed option that comfortably covers your work.

Reading a diagram or product photo

Drafting from visual references

Image-and-text conversations on Apple Silicon

In LocalEngine

Configured variants, by device.

The formats below are the downloads currently represented in LocalEngine’s model catalogs. GGUF runs through the llama.cpp-based runtime; MLX options use the Apple Silicon MLX runtime.

macOS

E2B · E4B · 12B · 26B-A4B · 31B

Formats: GGUF Q4_K_M / UD-Q4_K_M + BF16 projector · MLX 4-bit / 8-bit
Local note: The A4B edition is a mixture-of-experts model; MLX variants are tuned for Apple Silicon.

iPhone & iPad

E2B · E4B

Formats: GGUF Q4_K_M + BF16 projector · MLX 4-bit
Local note: E2B is the compact choice; E4B gives a newer device more room to reason over images.

About the source

Model identity, task category, supported formats, and license are based on the linked Hugging Face Gemma 4 collection and the LocalEngine macOS/iOS catalogs. Hardware guidance reflects the packaged variants, not a universal system requirement.