LLM Perks

Granite 3.0 3B A800M

Free right now Small
Open weights

Granite 3.0 3B A800M is a language model with 3B parameters from IBM. It is currently free at 1 provider with up to — tokens of context. Its weights are open, so it can also run locally.

Developer
IBM
Parameters
3B / 800M active
Type
Text
License
Open weights

Where to use Granite 3.0 3B A800M for free

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

ProviderContextLimitCard
NVIDIA Build
ibm/granite-3.0-3b-a800m-instruct
— 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": "ibm/granite-3.0-3b-a800m-instruct",
    "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 We do not publish our own estimates.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 Granite 3.0 3B A800M free?

Yes. As of September 26, 2026, Granite 3.0 3B A800M is free at NVIDIA Build. Each provider has its own limits — see the table above.

How do I call Granite 3.0 3B A800M via API?

Use any OpenAI-compatible client with base URL https://integrate.api.nvidia.com/v1, model ID ibm/granite-3.0-3b-a800m-instruct, and a NVIDIA Build key.

Is Granite 3.0 3B A800M open-weight?

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