ModelLLMsv1.0

Gemma 2B

by Google DeepMind · open-source · Last verified 2026-03-17

Gemma 2B is Google DeepMind's open-weight 2 billion parameter language model from the Gemma family, designed for lightweight deployment on devices with limited resources. It delivers strong performance for its size on language understanding and generation tasks, and serves as a foundation for fine-tuning on domain-specific tasks.

https://huggingface.co/google/gemma-2b ↗

C+

C+—Average

Adoption: B+Quality: B+Freshness: BCitations: BEngagement: F

Specifications

License: Gemma Terms of Use
Pricing: open-source
Capabilities: text-generation, instruction-following, fine-tuning, on-device-inference
Integrations: Hugging Face, Ollama, Google AI Studio, Vertex AI
Use Cases: on-device personal assistants, mobile AI features, fine-tuned specialized applications, developer experimentation
API Available: Yes
Parameters: ~2B
Context Window: 8K
Modalities: text
Training Cutoff: 2024
Tags: google, small, edge, open-source, gemma
Added: 2026-03-17
Completeness: 100%

Index Score

Adoption

Quality

Freshness

Citations

Engagement

Explore the full AI ecosystem on Agents as a Service