{"version":1,"type":"story","url":"https://digestai.news/story/defeating-nvidia-the-story-of-how-i-built-a-strata-ai-server-with-unpo","json":"https://digestai.news/story/defeating-nvidia-the-story-of-how-i-built-a-strata-ai-server-with-unpo.json","markdown":"https://digestai.news/story/defeating-nvidia-the-story-of-how-i-built-a-strata-ai-server-with-unpo.md","slug":"defeating-nvidia-the-story-of-how-i-built-a-strata-ai-server-with-unpo","headline":"Defeating NVIDIA? The story of how I built a Strata AI server with unpopular Radeon GPUs and had it build a 3D Minecraft game automatically for 140 yen in elect","summary":"The build cost between 280,000 and 320,000 yen and consumed only 140 yen in electricity over a 10‑hour autonomous run.\n\nDuring the run, the autonomous coding agent Hermes Agent generated 688,469 tokens, completing a 3‑D Minecraft‑style game in a browser. The system achieved 75 to 80+ tokens per second at full power and 35–54 tok/s while running VRChat simultaneously.\n\nThe article compares the cost of this local setup to cloud APIs: Claude Sonnet 5.5 with cache usage costs about 2,100 yen, Claude Opus 5.5 about 4,250 yen, and GPT‑6 Astra about 10,600 yen, versus 140 yen for local electricity. It highlights that Radeon GPUs can match or exceed NVIDIA performance for large‑scale models when paired with the right software.","keyPoints":["10‑hour autonomous run produced 688,469 tokens for 140 yen electricity","Strata engine enables AMD GPUs to match or exceed NVIDIA performance with 196,608‑token context"],"whyItMatters":"The story shows that high‑performance AI can be run on cheaper, widely available Radeon hardware, reducing cloud costs and expanding access for hobbyists and small labs.","category":{"slug":"hardware","name":"Hardware & Compute","url":"https://digestai.news/category/hardware"},"entities":{"companies":["AMD","NVIDIA","OpenAI","Anthropic","Amazon"],"models":["Strata","Hermes Agent","Qwen 3.8 Flash-Next","Claude Sonnet 5.5","GPT-6.1 Sol","Claude Opus 5.5"],"people":[]},"firstPublishedAt":"2026-11-02T01:03:00Z","updatedAt":"2026-11-02T01:03:00Z","sourceCount":1,"hasPrimarySource":false,"sources":[{"outlet":"note.com","title":"Defeating NVIDIA? The story of how I built a Strata AI server with unpopular Radeon GPUs and had it build a 3D Minecraft game automatically for 140 yen in electricity","url":"https://note.com/ozooooooooo/n/n0ee7f0389d19?hl=en","publishedAt":"2026-11-02T01:03:00Z","type":"press","primary":false,"lead":true}],"sourceNotes":null,"discussions":[],"thread":{"title":"AI Factory Showdown Across Hardware","url":"https://digestai.news/thread/nvidia-opens-vera-rubin-architecture-to-ocp-for-ai-factories","storyCount":4},"cite":{"text":"Digest AI, \"Defeating NVIDIA? The story of how I built a Strata AI server with unpopular Radeon GPUs and had it build a 3D Minecraft game automatically for 140 yen in elect\", 2 November 2026, https://digestai.news/story/defeating-nvidia-the-story-of-how-i-built-a-strata-ai-server-with-unpo","publisher":"Digest AI","title":"Defeating NVIDIA? The story of how I built a Strata AI server with unpopular Radeon GPUs and had it build a 3D Minecraft game automatically for 140 yen in elect","datePublished":"2026-11-02T01:03:00Z","url":"https://digestai.news/story/defeating-nvidia-the-story-of-how-i-built-a-strata-ai-server-with-unpo"},"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"}