{"version":1,"type":"story","url":"https://digestai.news/story/openai-gpt-oss-20b-runs-on-a-mac-mini","json":"https://digestai.news/story/openai-gpt-oss-20b-runs-on-a-mac-mini.json","markdown":"https://digestai.news/story/openai-gpt-oss-20b-runs-on-a-mac-mini.md","slug":"openai-gpt-oss-20b-runs-on-a-mac-mini","headline":"OpenAI gpt-oss:20b runs on a Mac mini","summary":"The author describes how to run OpenAI’s gpt-oss:20b model locally on a Mac mini (M6) with 32 GB of RAM using Ollama, Open WebUI, and the Python API.\n\nThe gpt-oss:20b model, which has about 21 billion parameters, fits on 12 GB of GPU memory and can be run without a Docker container. The author measured a total processing time of 16.28 seconds, an input speed of 260.42 tokens/second and a response speed of 38.80 tokens/second. The model can also be accessed through a browser interface via Open WebUI, which the author installed with Docker.\n\nThe post highlights the benefits of local inference—avoiding cloud API fees, reducing data leakage risk, and allowing custom integration through Python or HTTP APIs. It also notes that the model can be combined with RAG for document‑based queries, though the author has not yet set up the Open WebUI RAG API.","keyPoints":["gpt-oss:20b runs on a Mac mini with 32 GB RAM via Ollama","gpt-oss:20b has ~21 billion parameters and fits on 12 GB GPU memory","Local inference takes 16.28 s total, 260.42 tokens/s input, 38.80 tokens/s response"],"whyItMatters":"Local deployment of large OpenAI models on consumer hardware lets small businesses avoid cloud costs and data‑leakage concerns while still accessing powerful generative AI.","category":{"slug":"marketing","name":"Marketing & Small Business","url":"https://digestai.news/category/marketing"},"entities":{"companies":["OpenAI","Ollama","Open WebUI","Docker"],"models":["gpt-oss:20b","gpt-oss:120b","llama3.2","DrawThings"],"people":[]},"firstPublishedAt":"2026-10-20T17:47:00Z","updatedAt":"2026-10-20T17:47:00Z","sourceCount":1,"hasPrimarySource":false,"sources":[{"outlet":"note.com","title":"With Love (AI): Running OpenAI's AI models on a Mac mini!","url":"https://note.com/watabin/n/n5b2d0b9ea33e?hl=en","publishedAt":"2026-10-20T17:47:00Z","type":"press","primary":false,"lead":true}],"sourceNotes":null,"discussions":[],"thread":{"title":"Apple Macs Become Decentralized AI Cloud","url":"https://digestai.news/thread/user-tests-local-ai-on-apple-mac-studio-and-rtx-spark","storyCount":3},"cite":{"text":"Digest AI, \"OpenAI gpt-oss:20b runs on a Mac mini\", 20 October 2026, https://digestai.news/story/openai-gpt-oss-20b-runs-on-a-mac-mini","publisher":"Digest AI","title":"OpenAI gpt-oss:20b runs on a Mac mini","datePublished":"2026-10-20T17:47:00Z","url":"https://digestai.news/story/openai-gpt-oss-20b-runs-on-a-mac-mini"},"generatedBy":"Written by Digest AI's editorial model from the linked sources; the sources are the record.","license":"Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse"}