Qwen3-14B is a state-of-the-art large language model in the Qwen3 series, featuring 14.8 billion parameters and designed to deliver advanced reasoning, efficient dialogue, and robust multilingual support. It introduces a hybrid approach to problem-solving with two distinct modes: "thinking mode," which enables step-by-step reasoning for complex tasks such as mathematics, programming, and logical inference, and "non-thinking mode," designed for rapid, general-purpose responses. This flexibility allows users to optimize the model’s performance for either depth or speed, depending on the task at hand.
The model is fine-tuned for instruction-following, agent tool use, creative writing, and supports over 119 languages and dialects, making it highly versatile for global applications. Qwen3-14B natively supports a 32,000-token context window, which can be extended up to 131,000 tokens using YaRN-based scaling, enabling it to handle long documents and complex conversations efficiently. The model excels in agentic capabilities, coding, and multilingual tasks, and demonstrates superior alignment with human preferences in creative and interactive scenarios.
- Deployment of Qwen3-8B model using vLLM.
- Dependencies defined in
inferless-runtime-config.yaml
. - GitHub/GitLab template creation with
app.py
,inferless-runtime-config.yaml
andinferless.yaml
. - Model class in
app.py
withinitialize
,infer
, andfinalize
functions. - Custom runtime creation with necessary system and Python packages.
- Recommended GPU: NVIDIA A100 for optimal performance.
- Custom runtime selection in advanced configuration.
- Final review and deployment on the Inferless platform.
Get started by forking the repository. You can do this by clicking on the fork button in the top right corner of the repository page.
This will create a copy of the repository in your own GitHub account, allowing you to make changes and customize it according to your needs.
To access the custom runtime window in Inferless, simply navigate to the sidebar and click on the Create new Runtime button. A pop-up will appear.
Next, provide a suitable name for your custom runtime and proceed by uploading the inferless-runtime-config.yaml file given above. Finally, ensure you save your changes by clicking on the save button.
Log in to your inferless account, select the workspace you want the model to be imported into and click the Add a custom model
button.
- Select
Github
as the method of upload from the Provider list and then select your Github Repository and the branch. - Choose the type of machine, and specify the minimum and maximum number of replicas for deploying your model.
- Configure Custom Runtime ( If you have pip or apt packages), choose Volume, Secrets and set Environment variables like Inference Timeout / Container Concurrency / Scale Down Timeout
- Once you click “Continue,” click Deploy to start the model import process.
Enter all the required details to Import your model. Refer this link for more information on model import.
Following is an example of the curl command you can use to make inference. You can find the exact curl command in the Model's API page in Inferless.
curl --location '<your_inference_url>' \
--header 'Content-Type: application/json' \
--header 'Authorization: Bearer <your_api_key>' \
--data '{
"inputs": [
{
"name": "prompt",
"shape": [1],
"data": ["Give me a short introduction to large language model."],
"datatype": "BYTES"
}
]
}'
Open the app.py
file. This contains the main code for inference. The InferlessPythonModel
has three main functions, initialize, infer and finalize.
Initialize - This function is executed during the cold start and is used to initialize the model. If you have any custom configurations or settings that need to be applied during the initialization, make sure to add them in this function.
Infer - This function is where the inference happens. The infer function leverages both RequestObjects and ResponseObjects to handle inputs and outputs in a structured and maintainable way.
- RequestObjects: Defines the input schema, validating and parsing the input data.
- ResponseObjects: Encapsulates the output data, ensuring consistent and structured API responses.
Finalize - This function is used to perform any cleanup activity for example you can unload the model from the gpu by setting to None
.
For more information refer to the Inferless docs.