{"slug": "show-hn-i-indexed-37h-of-my-videos-using-an-rtx-4090-and-local-ml-models-in-24h", "title": "Show HN: I indexed 37h of my videos using an RTX 4090 and local ML models in 24h", "summary": "A developer indexed 37 hours of video content using an NVIDIA RTX 4090 and local ML models in 24 hours, processing long podcast episodes, coding tutorials, and screen recordings. The RTX 4090 significantly outperformed the M1 Max, with the longest 3-hour livestream indexed in under 2 hours.", "body_md": "TLDR: Following my recent blog post and Hacker News post ([https://news.ycombinator.com/item?id=48528029](https://news.ycombinator.com/item?id=48528029)). where I ran the desktop app on my M1 Max. This time, I’m using the self-hosted version, running in Docker, with an NVIDIA RTX 4090 (24 GB of VRAM).\n\nThe content is also fundamentally more demanding: long podcast episodes with at least two faces in every frame, coding tutorials packed with on-screen text, and screen recordings. GoPro footage is mostly wide outdoor shots.\n\nBut NVIDIA was much faster than my M1 Max.\n\nThe longest video was a livestream of 3h 12m indexed in 1h 52m (4,612 frames analyzed).\n\nYou can directly see the processing jobs results in JSON format here: [https://gist.github.com/IliasHad/fd64e4d331e90e57d61e95f64e8...](https://gist.github.com/IliasHad/fd64e4d331e90e57d61e95f64e8bf97a)\n\nComments URL: [https://news.ycombinator.com/item?id=48731129](https://news.ycombinator.com/item?id=48731129)\n\nPoints: 1\n\n# Comments: 1", "url": "https://wpnews.pro/news/show-hn-i-indexed-37h-of-my-videos-using-an-rtx-4090-and-local-ml-models-in-24h", "canonical_source": "https://news.ycombinator.com/item?id=48731129", "published_at": "2026-06-30 11:28:04+00:00", "updated_at": "2026-06-30 11:50:55.920876+00:00", "lang": "en", "topics": ["machine-learning", "computer-vision", "ai-infrastructure", "ai-tools", "developer-tools"], "entities": ["NVIDIA", "RTX 4090", "M1 Max", "Docker", "GoPro"], "alternates": {"html": "https://wpnews.pro/news/show-hn-i-indexed-37h-of-my-videos-using-an-rtx-4090-and-local-ml-models-in-24h", "markdown": "https://wpnews.pro/news/show-hn-i-indexed-37h-of-my-videos-using-an-rtx-4090-and-local-ml-models-in-24h.md", "text": "https://wpnews.pro/news/show-hn-i-indexed-37h-of-my-videos-using-an-rtx-4090-and-local-ml-models-in-24h.txt", "jsonld": "https://wpnews.pro/news/show-hn-i-indexed-37h-of-my-videos-using-an-rtx-4090-and-local-ml-models-in-24h.jsonld"}}