diff --git a/Dockerfile b/Dockerfile
new file mode 100644
index 00000000..0e1bd64d
--- /dev/null
+++ b/Dockerfile
@@ -0,0 +1,24 @@
+# Use a base image that includes Miniconda
+FROM continuumio/miniconda3
+
+# Set the working directory in the container
+WORKDIR /app
+
+RUN apt-get update && apt-get install -y cmake g++
+# Copy the environment.yml file into the container at /app
+COPY pyproject.toml CMakeLists.txt requirements.txt README.md ./
+COPY dependency ./dependency
+
+# Install the conda environment
+RUN conda create -n nexa python=3.10 -y
+RUN /bin/bash -c "source activate nexa && pip install -r requirements.txt && pip install -e ."
+
+# Activate the environment
+RUN echo "source activate nexa" > ~/.bashrc
+ENV PATH /opt/conda/envs/nexa/bin:$PATH
+
+# Copy your application code to the container
+COPY . .
+
+# Set the command to activate the environment and start your application
+CMD ["bash", "-c", "source activate nexa && python -m nexa.cli.entry gen-text gemma"]
\ No newline at end of file
diff --git a/README.md b/README.md
index 939d93db..d9d4330f 100644
--- a/README.md
+++ b/README.md
@@ -24,7 +24,7 @@ Detailed API documentation is available [here](docs/index.html).
 
 ## Installation
 
-**GPU version(optional)**
+### GPU version(optional)
 
 check if you have GPU acceleration (torch required)
 <details>
@@ -69,7 +69,7 @@ check if you have GPU acceleration (torch required)
   ```
 </details>
 
-**CPU version**
+### CPU version
 
 <details>
   <summary>Mac with Intel chips</summary>
@@ -92,6 +92,22 @@ Or you prefer to install the pre-built wheel:
 pip install nexaai --index-url https://nexaai.github.io/nexa-sdk/whl/cpu --extra-index-url https://pypi.org/simple
 ```
 
+### Docker Usage
+Note: Docker doesn't support GPU acceleration
+
+`docker pull nexa4ai/sdk:latest`
+
+replace following placeholder with your path and command
+
+`docker run -v <your_model_dir>:/model -it nexa4ai/sdk:latest [nexa_command] [your_model_relative_path]`
+
+Example:
+
+`docker run -v /home/ubuntu/.cache/nexa/hub/official:/model -it nexa4ai/sdk:latest nexa gen-text /model/Phi-3-mini-128k-instruct/q4_0.gguf`
+
+will create an interactive session with text generation
+```
+
 ## Nexa CLI commands
 
 ## Model Commands
diff --git a/pyproject.toml b/pyproject.toml
index 65a3c414..09fede53 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -80,6 +80,7 @@ sdist.exclude = [".github", "build", "dist", "nexa.egg-info", "dependency/llama.
 build.verbose = true
 cmake.build-type = "Release"
 cmake.version = ">=3.16"
+cmake.args = ["-DCMAKE_CXX_FLAGS=-fopenmp"]
 
 [tool.pytest.ini_options]
 testpaths = ["tests"]
\ No newline at end of file