Dedicated model · Available as managed deployment
NVIDIA's Nemotron 3 Super, a 120B mixture-of-experts with 12B active parameters, the balanced mid-tier for corporate agent workflows, shipped in NVFP4 and BF16. Available as a managed deployment: validated on AxForge hardware and deployed on a DGX Spark for your traffic only, as an OpenAI-compatible endpoint on hardware only you use, hosted in the EU.
Why Nemotron 3 Super
| The mid-tier for agents | 120B total, 12B active: large-model knowledge at a latency and cost that suits day-to-day agent traffic. |
|---|---|
| Fits one large-memory machine | The NVFP4 build is sized for a single dedicated machine such as a DGX Spark; the BF16 build for multi-GPU systems. |
| NVIDIA open model licence | Ships under NVIDIA's open model licence; AxForge reviews it with you and deploys under it where it applies. |
Specifications
| Model | Nemotron 3 Super by nvidia |
|---|---|
| Modalities | Text |
| Sizes | 67.2B, 123.6B |
| Released | 2026-03 |
| Popularity | 1.1M downloads / month on HuggingFace |
| Licence | Commercial licence needed (the model's own licence); AxForge handles the licence where one is required |
| Availability | Available as managed deployment, operated by AxForge on hardware reserved for you |
| Hardware | NVIDIA DGX Spark (GB10, 128 GB unified memory) in a quantized build, owned and operated by AxForge |
| Region | Málaga, Spain (eu-es-1) |
| Pricing | Hardware from €0.85/hour, rental term: Hour, week, month or year. Managed service quoted per deployment. Request deployment and we confirm both in writing. |
We publish only numbers we measure ourselves, and we haven't benchmarked this model on our nodes yet. For quality benchmarks, see the model card in the catalogue and the official card on HuggingFace.
Deployment
| System | A dedicated NVIDIA DGX Spark (GB10, 128 GB unified memory), reserved for you |
|---|---|
| Commercial model | Hour, week, month or year. Hardware from €0.85/hour, managed service quoted per deployment |
| Endpoint | OpenAI-compatible /v1 on your own machine, only your traffic |
| Location | Hosted in the EU: Málaga, Spain (eu-es-1) |
| Data handling | Zero prompt retention, same policy as the serverless API |
The model is validated on AxForge hardware and deployed on your system. After deployment, your endpoint speaks the OpenAI API with the model name you receive with the deployment.
Data & privacy
Prompts and completions are processed in memory in the EU, not written to disk, not logged, not retained, and never used to train anything. We keep only request metadata (token counts, timestamps, status) for billing and operations. The full policy is at axforge.ai/privacy.
FAQ
Not on the serverless API. It is available as a managed deployment: validated on AxForge hardware and deployed on a DGX Spark for your traffic only. The serverless API serves Qwen3.8 27B.
The NVFP4 build does; AxForge validates it on the Spark and scopes a multi-GPU system if your throughput needs it.
Super for balanced cost and speed, Ultra for the hardest reasoning and coding tasks on a multi-GPU system.
We publish only numbers we measure ourselves, and we haven't benchmarked this model on our nodes yet. For quality benchmarks, see the official model card.
A dedicated NVIDIA DGX Spark (GB10, 128 GB unified memory) rented by the hour, week, month or year, running Nemotron 3 Super behind an OpenAI-compatible endpoint on your own machine, hosted in the EU with zero prompt retention.
Hardware from €0.85/hour, by the hour, week, month or year; the managed service is quoted per deployment. Request deployment and we confirm both in writing.
Explore