Nemotron Nano 3 4B
Nemotron Nano 3 4B is NVIDIA's language model. A compact 4B-parameter third-generation Nemotron Nano model from NVIDIA, designed for efficient on-device reasoning and instruction-following tasks.
Capabilities
Input1/5
Text✓
Image·
Audio·
Video·
PDF·
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities0/13
Reasoning·
Adaptive Reasoning·
Function Calling·
Parallel Function Calling·
Structured Outputs·
Native JSON Schema·
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·
Cheapest Instances to Run It
Cloud GPU instances that can host Nemotron Nano 3 4B, ranked by cheapest on-demand price. The model needs about 10 GB of GPU memory at FP16 precision (estimated from its parameter count), so treat the fit as guidance rather than a guarantee.
All clouds
FP16 (full precision)
US Dollar ($)
Instance | Cloud | GPU | VRAM | Price | Cheapest region | |
|---|---|---|---|---|---|---|
| Standard_NV4as_v4 |  Azure | AMD Radeon Instinct MI25 | 16 GB | $0.233/hr | eastus | |
| g5g.xlarge |  AWS | T4g | 16 GB | $0.420/hr | us-east-1 | |
| Standard_NV8as_v4 | Azure | AMD Radeon Instinct MI25 | 16 GB | $0.466/hr | eastus | |
Versions
| Version | Released | Context | Input / 1M | Output / 1M | Status |
|---|---|---|---|---|---|
| Nemotron 4 15B | — | — | — | — | Available |
| Nemotron 3 Ultra 550B A55B | 1.0M | $0.500 | $2.20 | Available | |
| Nemotron 3.5 Content Safety | 128K | — | — | Available | |
| Nemotron Nano 3 30B A3B Omni Reasoning | 256K | — | — | Available | |
| Nemotron Super 3 120B | 256K | $0.150 | $0.650 | Available | |
| Nemotron Nano 3 30B | 262K | $0.060 | $0.240 | Available | |
| Nemotron Nano 3 4B | — | — | — | — | Current |
| Nemotron Nano 3 30B A3B Omni | — | — | — | — | Available |
| Nemotron Nano 3 30B A3B Reasoning | — | — | — | — | Available |
| Nemotron 3 | — | — | — | — | Available |
| Nemotron 3 Nano 30B A3B | — | — | — | — | Available |