gemma3:4b-cloud

Family context: Gemma 3 family

Publisher: Google DeepMind

Google documents Gemma 3 as a family with text-generation and, in its multimodal sizes, image-understanding functions. Context limits and input support must be read for the specific size.

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

Published family information

Published input context for 1B and 270M

32K tokens Source

Published input context for 4B, 12B and 27B

128K tokens Source

Output

Generated text Source

Publisher-described uses

• Question answering, summarization and image-understanding tasks in the applicable variants. Source

Reference limitations

• The 128K figure is not the context specification of the 1B variant. Family-level multimodal text should not be assigned indiscriminately to every size. 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 3 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 gemma3:4b-cloud comes from

Named in 4 observation pages

• 31 cloud models × 3 wrappers on the same audit · V1
• 3B-7B local models — all 53 · V1
• Cloud Models — three-judge autoresearch observation set · V1
• Tool-call format compatibility across 31 cloud models · V1