functiongemma:270m

Upstream reference: FunctionGemma

Publisher: Google DeepMind

Google positions FunctionGemma as a small foundation for task-specific function-calling models, using a distinct chat format and further tuning for the intended tool task.

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

Published upstream specifications

Upstream foundation named by Google

Gemma 3 270M Source

Documented input scope

Text-only function calling Source

Publisher-described uses

• Fine-tuning for specific function-calling and multi-turn tool workflows. Source

Reference limitations

• Google explicitly distinguishes it from a direct-dialogue model and states that task-specific fine-tuning is intended. Source

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

Publisher sources

• FunctionGemma 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 functiongemma:270m comes from

Named in 1 observation page

• Xeon vs AMD workstation — CPU inference head-to-head · V1