Llama 3.1 Nemotron Nano 4B v1.1 is
NVIDIA's language model. A compact 4B Nemotron Nano reasoning model from NVIDIA built on Llama 3.1, balancing small footprint with chain-of-thought reasoning capability.
14.4#194 |
50.0#80 |
0.6#207 |
0.4#247 |
0.1#169 |
0.5#92 |
0.7#19 |
0.3#242 |
0.00s#107 |
0.1#280 |
0.9#23 |
0.5#80 |
0.0#264 |
0.1#229 |
0.0#313 |
Capabilities
Input1/5
β
Β·
Β·
Β·
Β·
Output1/5
β
Β·
Β·
Β·
Β·
Capabilities0/13
Β·
Β·
Β·
Β·
Β·
Β·
Β·
Β·
Β·
Β·
Β·
Β·
Β·
Versions
| Version | Released | Context | Input / 1M | Output / 1M | Status |
|---|---|---|---|---|---|
| Nemotron 2 Nano 12B VL | 131K | β | β | Available | |
| Nemotron 3 Nano 30B | 262K | β | β | Available | |
| Llama 3.1 Nemotron Nano 4B v1.1 | β | β | β | β | Current |
Other models
| Model | Tier | Released | Context | Input / 1M | Output / 1M |
|---|---|---|---|---|---|
| Nemotron 4 15B | β | β | β | β | β |
| Nemotron Super 3 120B | β | 256K | $0.150 | $0.650 | |
| Nemotron Super 3 120B A12B | β | 262K | $0.090 | $0.450 | |
| Nemotron Nano 3 30B | β | 262K | $0.060 | $0.240 | |
| Nemotron 3 Nano 30B A3B | β | 262K | $0.050 | $0.200 | |
| Nemotron 3 | β | β | β | β | β |
| Nemotron 3 Super | Super | β | β | β | β |
| Nemotron 3 Super 120B | Super | β | β | β | β |
| Nemotron 3 Super 120B A12B | Super | β | β | β | β |
| Nemotron Cascade 2 30B A3B | β | β | β | β | β |