gemma4:31b-cloud

Family context: Gemma 4 family

Publisher: Google DeepMind

Google’s Gemma 4 overview describes several architectures for different resource settings. The documented 31B configuration is dense; other family members use different parameter and modality designs.

Publisher-described context, separate from Sigma5C observations and recorded catalog statistics.

Published family information

Named 31B configuration

Dense model Source

Other documented architecture types

Effective-parameter small models and mixture-of-experts configurations Source

Publisher-described uses

• Question answering, summarization and multimodal text-generation workflows described by Google. Source

Reference limitations

• A family configuration does not verify which checkpoint or inputs a cloud runtime currently exposes. Source

A recorded tag and an upstream card association do not verify the deployed checkpoint, quantization, configured context or current hosted availability.

Publisher sources

• Gemma 4 family official documentation — Google DeepMind. Checked 2026-11-02.

Links

Recorded references do not establish downloadable weights, licensing or current availability.

• Google AI / Google DeepMind — official site
• Ollama
• Provider page
• Hugging Face
• Official model announcement / documentation

Where gemma4:31b-cloud comes from

Named in 1 observation page

• Function-calling — 9 cloud models × 30 prompts · V1