---
pipeline_tag: text-generation
base_model:
- Qwen/Qwen3.6-27B
license: apache-2.0
library_name: Model Optimizer
tags:
- ModelOpt
- Qwen3.6
- quantized
- FP4
- fp4
---

# Model Overview

## Description:
The **mmangkad/Qwen3.6-27B-NVFP4** model is a quantized version of Alibaba's Qwen3.6-27B model, an auto-regressive language model that uses an optimized transformer architecture. For more information on the base model, please check [here](https://huggingface.co/Qwen/Qwen3.6-27B). This model was quantized using the [NVIDIA Model Optimizer](https://github.com/NVIDIA/Model-Optimizer).

This model is ready for commercial/non-commercial use.  <br>

## Third-Party Community Consideration
This model is built upon a third-party base model; see the link to the Non-NVIDIA [(Qwen3.6-27B) Model Card](https://huggingface.co/Qwen/Qwen3.6-27B) for original requirements and use cases.

### License/Terms of Use:
[Apache license 2.0](https://huggingface.co/datasets/choosealicense/licenses/blob/main/markdown/apache-2.0.md)

### Deployment Geography:
Global <br>

### Use Case: <br>
Developers looking to take off-the-shelf, pre-quantized models for deployment in AI Agent systems, chatbots, RAG systems, and other AI-powered applications. <br>

### Release Date:  <br>
Huggingface 04/22/2026 via https://huggingface.co/mmangkad/Qwen3.6-27B-NVFP4 <br>

## Model Architecture:
**Architecture Type:** Transformers  <br>
**Network Architecture:** Qwen3.6-27B <br>
**Number of Model Parameters:** 27B <br>

## Input:
**Input Type(s):** Text <br>
**Input Format(s):** String <br>
**Input Parameters:** One-Dimensional (1D) <br>
**Other Properties Related to Input:** Context length up to 262K <br>

## Output:
**Output Type(s):** Text <br>
**Output Format:** String <br>
**Output Parameters:** 1D (One-Dimensional): Sequences <br>
**Other Properties Related to Output:** N/A <br>

This AI model is 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. <br>

## Software Integration:
**Supported Runtime Engine(s):** <br>
* SGLang <br>

**Supported Hardware Microarchitecture Compatibility:** <br>
* NVIDIA Blackwell <br>

**Preferred Operating System(s):** <br>
* Linux <br>

## Model Version(s):
The model is quantized with nvidia-modelopt **v0.42.0rc1.dev107+g3c5d36680** <br>

## Training, Testing, 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) <br>
** Data Collection Method by dataset: Automated. <br>
** Labeling method: Automated. <br>
** 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. <br>

## Training Dataset:
** Data Modality: Undisclosed <br>
** Data Collection Method by dataset: Undisclosed <br>
** Labeling Method by dataset: Undisclosed<br>
** Properties: Undisclosed

## Testing Dataset:
** Data Collection Method by dataset: Undisclosed <br>
** Labeling Method by dataset: Undisclosed <br>
** Properties: Undisclosed <br>

## Evaluation Dataset:
** Data Collection Method by dataset: Hybrid: Human, Automated <br>
** Labeling Method by dataset: Hybrid: Human, Automated <br>
** Properties: Evaluated on benchmarks including GPQA, which is a dataset of 448 multiple-choice questions written by domain experts in biology, physics, and chemistry. <br>

## Inference:
**Engine:** SGLang <br>
**Test Hardware:** B300 <br>

## Post Training Quantization
This model was obtained by quantizing the weights and activations of Qwen3.6-27B to NVFP4 data type, ready for inference with SGLang. Only the weights and activations of the linear operators within transformer blocks are quantized.

## Usage

To serve this checkpoint with [SGLang](https://github.com/sgl-project/sglang), you need to use the latest main branch and run the sample command below:

```sh
sglang serve --model-path mmangkad/Qwen3.6-27B-NVFP4 --reasoning-parser qwen3 --tool-call-parser qwen3_coder --quantization modelopt_fp4
```

## Model Limitations:

The base model was trained on data that contains toxic language and societal biases originally crawled from the internet. Therefore, the model may amplify those biases and return toxic responses, especially when prompted with toxic prompts. The model may generate answers that may be inaccurate, omit key information, or include irrelevant or redundant text producing socially unacceptable or undesirable text, even if the prompt itself does not include anything explicitly offensive.

## Ethical Considerations

Trustworthy AI is a shared responsibility. When downloaded or used in accordance with the Apache 2.0 license, developers should work to ensure this model meets requirements for the relevant industry and use case and addresses unforeseen product misuse.