NVIDIA · Released Aug 21, 2024Nemotron Mini 4B Instruct
Compact Nemotron model for efficient reasoning and deployable AI agents.
- Capability
- —No ECI score yet
- Input
- Freeper 1M tokens
- Output
- Freeper 1M tokens
- Context
- 128K8K max output
What it costs
- Input
- Freeper million tokens
- Output
- Freeper million tokens
Listed as free on Nvidia’s own API.
Independent benchmarks
Epoch AI has not published a Capabilities Index score for Nemotron Mini 4B Instruct yet.
The details
- Lab
- NVIDIA
- Released
- Aug 21, 2024
- Context window
- 128,000 tokens
- Max output
- 8,192 tokens
- Inputs
- Text
- Output
- Text
- Reasoning
- No
- Tool calling
- Yes
- Structured output
- No
- Weights
- Open weights
- API model ID
nvidia/nemotron-mini-4b-instructon Nvidia- Availability
- 1 API providerlisted on models.dev
- Status
- Deprecated by the provider
More from NVIDIA
About Nemotron Mini 4B Instruct
How much does Nemotron Mini 4B Instruct cost?
Nemotron Mini 4B Instruct is listed as free on Nvidia.
What is the context window of Nemotron Mini 4B Instruct?
Nemotron Mini 4B Instruct accepts up to 128,000 tokens per request and can write up to 8,192 tokens in one response.
How good is Nemotron Mini 4B Instruct?
Epoch AI has not published a Capabilities Index score for Nemotron Mini 4B Instruct yet.
Is Nemotron Mini 4B Instruct open source?
Yes. NVIDIA publishes the weights, so it can be downloaded and self-hosted.
What inputs does Nemotron Mini 4B Instruct support?
Nemotron Mini 4B Instruct accepts text and replies in text. It is not a dedicated reasoning model, supports tool calling.
When was Nemotron Mini 4B Instruct released?
NVIDIA released Nemotron Mini 4B Instruct on Aug 21, 2024.
What are the best alternatives to Nemotron Mini 4B Instruct?
The closest current models from other labs on capability, price and release date are GLM-4.5-Flash (Z.ai (Zhipu), Free / Free), o3-deep-research (OpenAI), Aya Expanse 8B (Cohere) and Vision Large (Vispark).