gemma:2b

Family context: Original Gemma family

Publisher: Google

The original Gemma card describes English text-to-text decoder language models with separate pretrained and instruction-tuned variants.

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

Published family information

Input/output role

Text input and generated English text Source

Release structure

Separate pretrained and instruction-tuned checkpoints Source

Publisher-described uses

• Question answering, summarization and text-generation research. Source

Reference limitations

• The original 2B HF files were not accessible in this unauthenticated pass. This is family context from Google’s public original Gemma card; no later Gemma vision/context specifications are assigned. Source

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

Publisher sources

• Original Gemma family official documentation — Google. 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 gemma:2b comes from

Named in 2 observation pages

• A consumer GPU recorded higher throughput than a 48-core Xeon · V1
• NVIDIA GTX 1070 — 344 models profiled · V1