---
pipeline_tag: text-generation
base_model:
- deepseek-ai/DeepSeek-V4-Pro
license: mit
library_name: Model Optimizer
tags:
- nvidia
- ModelOpt
- DeepSeekV4
- quantized
- NVFP4
- nvfp4
---
# Model Overview
## Description:
The NVIDIA DeepSeek-V4-Pro-NVFP4 model is the quantized version of the DeepSeek-V4-Pro model, which is a Mixture-of-Experts (MoE) language model with 1.6 trillion total parameters and 49 billion activated parameters. For more information, please check [here](https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro). The NVIDIA DeepSeek V4 Pro NVFP4 model is quantized with [Model Optimizer](https://github.com/NVIDIA/Model-Optimizer).
This model is ready for commercial/non-commercial use.
## Third-Party Community Consideration
This model is not owned or developed by NVIDIA. This model has been developed and built to a third-party’s requirements for this application and use case; see link to Non-NVIDIA [(DeepSeek V4 Pro) Model Card](https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro).
### License/Terms of Use:
[MIT](https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro/blob/main/LICENSE)
### Deployment Geography:
Global
### Use Case:
DeepSeek V4 is well-suited for advanced reasoning, agentic AI applications, tool use scenarios, and complex problem-solving in domains such as mathematics, software engineering, and enterprise AI assistants.
### Release Date:
Huggingface 05/27/2026 via https://huggingface.co/nvidia/DeepSeek-V4-Pro-NVFP4
## Model Architecture:
**Architecture Type:** Transformers
**Network Architecture:** Mixture-of-Experts (MoE) with Hybrid Attention (Compressed Sparse Attention + Heavily Compressed Attention)
**Total Parameters:** 1.6 Trillion (49 Billion activated)
## Input:
**Input Type(s):** Text
**Input Format(s):** String
**Input Parameters:** 1D (One Dimensional)
**Other Properties Related to Input:** Supports multi-turn conversations with system prompts, user messages, and assistant responses. Maximum context length of 1 million tokens. Uses a custom encoding pipeline (encoding_dsv4) with three reasoning modes: Non-think (fast), Think High (logical analysis), and Think Max (full reasoning extent).
## Output:
**Output Type(s):** Text
**Output Format:** String
**Output Parameters:** 1D (One Dimensional)
**Other Properties Related to Output:** Supports structured JSON output, function/tool calling, and reasoning content when enabled.
Our AI models are designed and/or optimized to run on NVIDIA GPU-accelerated systems. By leveraging NVIDIA’s hardware (e.g. GPU cores) and software frameworks (e.g., CUDA libraries), the model achieves faster training and inference times compared to CPU-only solutions.
## Software Integration:
**Supported Runtime Engine(s):**
* SGLang
* vLLM
**Supported Hardware Microarchitecture Compatibility:**
* NVIDIA Blackwell
**Preferred Operating System(s):**
* Linux
The integration of foundation and fine-tuned models into AI systems requires additional testing using use-case-specific data to ensure safe and effective deployment. Following the V-model methodology, iterative testing and validation at both unit and system levels are essential to mitigate risks, meet technical and functional requirements, and ensure compliance with safety and ethical standards before deployment.
## Model Version(s):
** The model is quantized DeepSeek-V4-Pro-NVFP4 with nvidia-modelopt **v0.44**
## Training and Evaluation Datasets:
## Calibration Dataset:
** Link: [cnn_dailymail](https://huggingface.co/datasets/abisee/cnn_dailymail), [Nemotron-Post-Training-Dataset-v2](https://huggingface.co/datasets/nvidia/Nemotron-Post-Training-Dataset-v2)
** Data Collection Method by dataset: Automated.
** Labeling Method by dataset: Automated.
** Properties: The cnn_dailymail dataset is an English-language dataset containing just over 300k unique news articles as written by journalists at CNN and the Daily Mail. The Nemotron-Post-Training-Dataset-v2 is a post-training dataset curated by NVIDIA containing multi-turn conversations across diverse topics.
## Training Dataset:
**Data Modality:** Undisclosed
**Data Collection Method by dataset:** Hybrid: Human, Automated
**Labeling Method by dataset:** Hybrid: Human, Automated
## Testing Dataset:
**Data Collection Method by dataset:** Hybrid: Human, Automated
**Labeling Method by dataset:** Hybrid: Human, Automated
**Dataset Properties:** Undisclosed
## Evaluation Dataset:
**Data Collection Method by dataset:** Hybrid: Human, Automated
**Labeling Method by dataset: Hybrid:** Human, Automated
**Dataset Properties:** We evaluated the model on text-based reasoning, coding, and agentic tool-use benchmarks: GPQA Diamond contains 448 graduate-level multiple-choice questions written by domain experts in biology, physics, and chemistry; AA-LCR (Artificial Analysis Long Context Recall) evaluates a model's ability to accurately retrieve and recall information from long input contexts; τ²-Bench Telecom evaluates agentic tool-use and policy-adherence capabilities in dual-control telecom customer-service scenarios where the model interacts with a simulated user and external tools to resolve account issues; SciCode evaluates scientific coding capabilities; IFBench is a benchmark for evaluating instruction-following capabilities across diverse and structured task constraints.
## Inference:
**Acceleration Engine:** SGLang, vLLM
**Test Hardware:** NVIDIA Blackwell B200
## Post Training Quantization
This model was obtained by quantizing the weights and activations of DeepSeek-V4-Pro to NVFP4 data type, ready for inference with SGLang and vLLM. Only the weights and activations of the linear operators within transformer blocks in MoE are quantized.
## Usage
### Deploy with vLLM
```sh
python -m vllm.entrypoints.cli.main serve \
nvidia/DeepSeek-V4-Pro-NVFP4 \
--tensor-parallel-size 8 \
--trust-remote-code \
--kv-cache-dtype fp8 \
--served-model-name nvfp4
```
### Deploy with SGLang
Requires [SGLang PR #25820](https://github.com/sgl-project/sglang/pull/25820). The integration auto-detects NVFP4 from the checkpoint's `hf_quant_config.json` (weights are stored in FP8 with `"moe_quant_algo": "NVFP4"`):
```sh
python3 -m sglang.launch_server --model nvidia/DeepSeek-V4-Pro-NVFP4 --tensor-parallel-size 8 --trust-remote-code
```
### Evaluation
The accuracy benchmark results are presented in the table below:
| Precision | GPQA Diamond | AA-LCR | τ²-Bench Telecom | SciCode | IFBench |
| FP8 (AA Ref) | 89.00 | 66.00 | 96.00 | 50.00 | 76.00 |
| FP8 (Ours) | 89.49 | 66.89 | 94.25 | 51.08 | 77.82 |
| NVFP4 | 89.33 | 66.33 | 94.83 | 53.45 | 77.21 |