{"id":17443984,"url":"https://github.com/alpine-docker/ollama","last_synced_at":"2025-08-03T20:30:35.939Z","repository":{"id":258044960,"uuid":"871605615","full_name":"alpine-docker/ollama","owner":"alpine-docker","description":"Minimal CPU-only Ollama Docker Image","archived":false,"fork":false,"pushed_at":"2024-10-25T02:53:25.000Z","size":18,"stargazers_count":2,"open_issues_count":1,"forks_count":1,"subscribers_count":1,"default_branch":"master","last_synced_at":"2024-12-06T13:47:44.324Z","etag":null,"topics":["cpu-only","docker","llama3","ollama"],"latest_commit_sha":null,"homepage":"https://hub.docker.com/repository/docker/alpine/ollama/general","language":"Roff","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/alpine-docker.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":".github/FUNDING.yml","license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null},"funding":{"github":["ozbillwang"],"custom":["https://www.buymeacoffee.com/ozbillwang","https://github.com/sponsors/ozbillwang"]}},"created_at":"2024-10-12T12:35:22.000Z","updated_at":"2024-12-05T14:09:57.000Z","dependencies_parsed_at":"2024-10-17T12:39:32.071Z","dependency_job_id":"b54e95c8-771e-4164-91ad-79f8da463a37","html_url":"https://github.com/alpine-docker/ollama","commit_stats":null,"previous_names":["alpine-docker/ollama"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/alpine-docker%2Follama","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/alpine-docker%2Follama/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/alpine-docker%2Follama/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/alpine-docker%2Follama/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/alpine-docker","download_url":"https://codeload.github.com/alpine-docker/ollama/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":228561598,"owners_count":17937178,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["cpu-only","docker","llama3","ollama"],"created_at":"2024-10-17T17:04:55.900Z","updated_at":"2025-08-03T20:30:35.925Z","avatar_url":"https://github.com/alpine-docker.png","language":"Roff","funding_links":["https://github.com/sponsors/ozbillwang","https://www.buymeacoffee.com/ozbillwang"],"categories":[],"sub_categories":[],"readme":"# Minimal CPU-only Ollama Docker Image\n\nThis repository provides a **minimal CPU-only Ollama Docker image**, specifically designed to run on systems without GPU support. At just **70MB**, this image is significantly smaller than the official Ollama image, which is around **4GB**.\n\n```\nollama latest b99944c07117   3 hours ago    69.3MB\n```\n## Notes\n\n* **This image is not based on alpine**, but [wolfi.dev](https://wolfi.dev/), I will work it out with alpine later\n* Got big help from @kth8 ( https://github.com/ollama/ollama/issues/7184#issuecomment-2414823298 )\n\n## Why Use This Image?\n\n1. **Lightweight**: The official Ollama image is over 4GB in size, which can be overkill for systems that only need CPU-based processing. This image is only **70MB**, making it much faster to download and deploy.\n   \n2. **CPU-only Support**: This image is tailored for systems without GPUs. It ensures you can run Ollama efficiently, even on basic or resource-constrained environments, without needing specialized hardware.\n\n3. **Run Anywhere**: Whether you're working on local servers, edge devices, or cloud environments that don’t offer GPU resources, this image allows you to **run Ollama anywhere**, focusing purely on CPU-based operations.\n\n## How to Use\n\n* Pull the image\n```bash\ndocker pull alpine/ollama\n```\n\n* Run the service with API supported\n\n```\ndocker rm -f ollama\ndocker run -d -p 11434:11434 -v ~/.ollama/root/.ollama --name ollama alpine/ollama\n```\n\n* Download the models, for example, `llama3.2`, only run once. It will save the model locally, you can re-use it later.\n\n```\ndocker exec -ti ollama ollama pull llama3.2\n```\n\n* Test its API service with curl \n```\n$ curl http://localhost:11434/api/generate -d '{\n  \"model\": \"llama3.2\",\n  \"prompt\":\"Why is the sky blue?\"\n}'\n\n{\"model\":\"llama3.2\",\"created_at\":\"2024-10-16T00:25:58.59931201Z\",\"response\":\"The\",\"done\":false}\n{\"model\":\"llama3.2\",\"created_at\":\"2024-10-16T00:25:58.695826838Z\",\"response\":\" sky\",\"done\":false}\n{\"model\":\"llama3.2\",\"created_at\":\"2024-10-16T00:25:58.780917761Z\",\"response\":\" appears\",\"done\":false}\n{\"model\":\"llama3.2\",\"created_at\":\"2024-10-16T00:25:58.992556209Z\",\"response\":\" blue\",\"done\":false}\n{\"model\":\"llama3.2\",\"created_at\":\"2024-10-16T00:25:59.085970606Z\",\"response\":\" because\",\"done\":false}\n{\"model\":\"llama3.2\",\"created_at\":\"2024-10-16T00:25:59.30869749Z\",\"response\":\" of\",\"done\":false}\n...\n```\n\nIf you monitor the CPU usage, for example, with [htop](https://htop.dev/), you would see the high CPU usage\n\nYou can deploy the Ollama web UI to chat with it directly. There are many tools available, but I won't recommend any specific one.\n\n## Use case\n\nthis image could be deployed to any enviornment, for example, in kubernetes cluster, you can use it to analyze logs, streamlining logs with local LLMs, etc.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Falpine-docker%2Follama","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Falpine-docker%2Follama","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Falpine-docker%2Follama/lists"}