ollama
Ollama Overview
Secure your stack with a hardened Ollama image freshly-built by Minimus. Minimus images always include the most up-to-date package version for all packages and dependencies contained in the image.
Use this image to run large language models (LLMs) locally. Currently, the Minimus Ollama image supports NVIDIA GPUs. An ROCm variant that can run Ollama on AMD GPUs is planned in the future.
Try It Out
The Minimus Ollama image is usually run on a machine equipped with an NVIDIA GPU with the CUDA toolkit. This is not required but highly recommended. If you're using a cloud service provider, we recommend using a VM with the CUDA drivers pre-installed. For more information on configuring the NVIDIA drivers see the NVIDIA guide for configuring a host system and Docker.
Take the Minimus Ollama image for a test run utilizing the flag --gpus=all to enable GPU acceleration:
docker run -d --gpus=all \
-v ollama:/ollama/.ollama -p 11434:11434 \
--name minimus-ollama \
reg.mini.dev/ollamaIf you get the error docker: Error response from daemon: could not select device driver "" with capabilities: [[gpu]], this means you don't have a compatible GPU driver. Skip ahead to see how to run Ollama without a GPU.
You can now run an LLM model and interact with it, for example Llama 3:
docker exec -it minimus-ollama ollama run llama3You can now chat with Llama 3 — an advanced AI language model designed for conversation.
Run Ollama without a GPU
Ollama will automatically fall back to CPU if no GPU is available. Note that performance on CPU will be slower and limited to smaller models.
To run the Minimus Ollama image without a GPU, drop the flag --gpus:
docker run -d \
-v ollama:/ollama/.ollama \
-p 11434:11434 --name minimus-ollama \
reg.mini.dev/ollamaVisit http://localhost:11434 in your browser to see the message Ollama is running.
Technical Considerations
The Ollama image provided by Minimus is a slim, security-hardened alternative to the public image from Docker Hub. The images are largely interchangeable, with a few differences as noted below.
Ollama built by Minimus:
- Runs as non-root by default for a security-first approach that protects against privilege escalation attacks. The public image runs as root.
- Drill down on the version specification tab to see the default user, listening ports, entrypoint, volumes, environment variables, etc.
The Payoff
A hardened, minimal image that will remain more secure for the long run and accrue vulnerabilities at a slower rate.
- See the risk reduction dashboard for a detailed CVE comparison over the past 30 days.
- Review the compliance report to see the default hardening and security configurations for the image.
Terms & Info
Trademark
This catalog is published by Minimus. All product names, logos, and marks, other than those belonging to Minimus, shown are owned by their respective rights holders and appear here only to identify the open source software each image contains. Minimus claims no ownership of those marks and implies no affiliation with, endorsement by, certification by, or sponsorship by any rights holder.
Disclaimer
Images are provided "as-is" without warranty of any kind. "Hardened" refers to the security configuration applied at the time of build and does not constitute a guarantee of ongoing security or absence of vulnerabilities. The free tier is provided without support, SLA, or guaranteed patching timelines. Security updates may be applied to paid subscriptions before or instead of free tier images. By pulling or using any image you agree to our Terms of Use.