LLM Perks

RecurrentGemma 2B

Google DeepMind · All Gemma models
Free right now Small
Open weights

RecurrentGemma 2B is a language model with 2B parameters from Google DeepMind. It is currently free at 1 provider with up to — tokens of context. Its weights are open, so it can also run locally.

Developer
Google DeepMind
Parameters
2B
Type
Text
License
Open weights

Where to use RecurrentGemma 2B for free

Each row is a separate free endpoint with its own limits.

ProviderContextLimitCard
NVIDIA Build
google/recurrentgemma-2b
— Free serverless inference for development; limits and model availability may change. No Open

Quick start

curl https://integrate.api.nvidia.com/v1/chat/completions \
  -H "Authorization: Bearer $NVIDIA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "google/recurrentgemma-2b",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Example for NVIDIA Build. Any OpenAI-compatible client works: Cursor, Cline, OpenCode, Open WebUI.

Benchmarks

This model is not on the Artificial Analysis leaderboard yet. We do not publish our own estimates.

Similar free models

FAQ

Is RecurrentGemma 2B free?

Yes. As of October 31, 2026, RecurrentGemma 2B is free at NVIDIA Build. Each provider has its own limits — see the table above.

How do I call RecurrentGemma 2B via API?

Use any OpenAI-compatible client with base URL https://integrate.api.nvidia.com/v1, model ID google/recurrentgemma-2b, and a NVIDIA Build key.

Is RecurrentGemma 2B open-weight?

Yes, the weights are published — you can download and run it locally, for example with Ollama or LM Studio.