{
 "schema_version": 1,
 "generated": "2026-10-20",
 "repo": "Yamz-Labs/kyojin",
 "name": "kyojin",
 "owner": "Yamz-Labs",
 "slug": "yamz-labs-kyojin",
 "github": "https://github.com/Yamz-Labs/kyojin",
 "what": "Kyojin is an open source inference engine, built on ExLlamaV3, that runs large GLM, Qwen and MiMo models on one AMD Strix Halo mini PC with 128 GB of memory.",
 "why": "",
 "language": "Python",
 "requirements": [
  "AMD Ryzen AI Max+ 395 mini PC with 128 GB of memory (Strix Halo, gfx1151)",
  "ROCm build of torch, installed per doc/install.md",
  "Python and the hf command-line tool to download model packs",
  "Roughly 100 GB of free disk space for a model pack (Qwen pack is 95 GB)"
 ],
 "audience_note": "Written for developers and self-hosters who own an AMD Ryzen AI Max+ 395 machine with 128 GB and want a local OpenAI-compatible model server.",
 "risk": "dual-use",
 "section": "earlier",
 "weekly_rank": null,
 "category": "Software and DevOps",
 "url": "https://dedupedai.com/use-cases/yamz-labs-kyojin/",
 "use_case_count": 5,
 "use_cases": [
  {
   "id": "yamz-labs-kyojin--run-local-openai-compatible-server",
   "title": "Run a local OpenAI-style LLM server on AMD",
   "best": true,
   "url": "https://dedupedai.com/use-cases/yamz-labs-kyojin/run-local-openai-compatible-server/",
   "json": "https://dedupedai.com/use-cases/u/yamz-labs-kyojin/run-local-openai-compatible-server.json"
  },
  {
   "id": "yamz-labs-kyojin--analyze-500k-token-documents-locally",
   "title": "Read a 500K-token document in one prompt",
   "best": false,
   "url": "https://dedupedai.com/use-cases/yamz-labs-kyojin/analyze-500k-token-documents-locally/",
   "json": "https://dedupedai.com/use-cases/u/yamz-labs-kyojin/analyze-500k-token-documents-locally.json"
  },
  {
   "id": "yamz-labs-kyojin--benchmark-and-share-strix-halo-results",
   "title": "Benchmark a Strix Halo machine and share results",
   "best": false,
   "url": "https://dedupedai.com/use-cases/yamz-labs-kyojin/benchmark-and-share-strix-halo-results/",
   "json": "https://dedupedai.com/use-cases/u/yamz-labs-kyojin/benchmark-and-share-strix-halo-results.json"
  },
  {
   "id": "yamz-labs-kyojin--monitor-local-inference-server-metrics",
   "title": "Scrape server metrics from a local model host",
   "best": false,
   "url": "https://dedupedai.com/use-cases/yamz-labs-kyojin/monitor-local-inference-server-metrics/",
   "json": "https://dedupedai.com/use-cases/u/yamz-labs-kyojin/monitor-local-inference-server-metrics.json"
  },
  {
   "id": "yamz-labs-kyojin--load-less-restricted-model-for-testing",
   "title": "Load a less-restricted model variant locally",
   "best": false,
   "url": "https://dedupedai.com/use-cases/yamz-labs-kyojin/load-less-restricted-model-for-testing/",
   "json": "https://dedupedai.com/use-cases/u/yamz-labs-kyojin/load-less-restricted-model-for-testing.json"
  }
 ],
 "disclaimer": "Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk."
}