Open weights · checked 20 Aug 2026
NVIDIA open-source models on Hugging Face
7 open-weight models
NVIDIA publishes the weights of 7 models in our catalogue, out of 16. Licences: other (5), llama3.1 (1) and apache-2.0 (1). None of them has a hosted standard-tier price in our catalogue yet.
| Model | Licence | Context | Input / 1M | Output / 1M | Grid | Weights |
|---|---|---|---|---|---|---|
| Gemma 4 31B IT NVFP4NVIDIA · open weights | other | — | — | — | — | Hugging Face ↗ |
| Llama 3_1 Nemotron Ultra 253B v1NVIDIA · open weights | other | 131K | — | — | — | Hugging Face ↗ |
| Llama 3_3 Nemotron Super 49B v1_5NVIDIA · open weights | other | 131K | — | — | — | Hugging Face ↗ |
| Llama 3.1 Nemotron 70B InstructNVIDIA · open weights | llama3.1 | — | — | — | — | Hugging Face ↗ |
| NVIDIA Nemotron 3 Super 120B A12B NVFP4NVIDIA · open weights | other | 262K | — | — | — | Hugging Face ↗ |
| NVIDIA Nemotron Nano 9B v2NVIDIA · open weights | other | 131K | — | — | — | Hugging Face ↗ |
| Qwen3.6 35B A3B NVFP4NVIDIA · open weights | apache-2.0 | — | — | — | — | Hugging Face ↗ |
Hosted models first, cheapest standard-tier input price first. “—” means we hold no hosted price or context window for it yet.Suggest a correction
Other open-weight makers
Questions
Is NVIDIA open source?
7 of the 16 NVIDIA models in our catalogue are marked open-weight, under other (5), llama3.1 (1) and apache-2.0 (1). The weights are public; what you may do with them is set by each licence.
Where can I download NVIDIA models?
On Hugging Face. Every model on this page links its weights there.
Can I use NVIDIA open-weight models through an API?
None of them has a hosted standard-tier price in our catalogue yet.
Which NVIDIA open-weight model has the largest context window?
NVIDIA Nemotron 3 Super 120B A12B NVFP4, at 262,144 tokens.