{
 "schema_version": 1,
 "generated": "2026-10-20",
 "repo": "surya-koritala/Glyd",
 "name": "Glyd",
 "owner": "surya-koritala",
 "slug": "surya-koritala-glyd",
 "github": "https://github.com/surya-koritala/Glyd",
 "what": "Glyd is a Rust library and CLI that keeps bf16 model weights and KV cache in fewer bits on the GPU, restoring exact values as the model runs, and also serves as a lossless file compressor.",
 "why": "",
 "language": "Rust",
 "requirements": [
  "Linux (x86_64 or aarch64) with an NVIDIA GPU: Ampere, Ada, Hopper or Blackwell, driver 580 or newer",
  "For the Python and vLLM steps: Python with pip, and vLLM for serving",
  "For the codec: Homebrew or a release tarball from the Glyd releases",
  "A Glyd license from suryakoritala@getglyd.com if the work is commercial, since the README says commercial use needs one"
 ],
 "audience_note": "Engineers running open-weight models on NVIDIA GPUs who need more context or room for more requests, and developers who want a smaller lossless alternative to zstd for large JSON files.",
 "risk": "none",
 "section": "earlier",
 "weekly_rank": null,
 "category": "Software and DevOps",
 "url": "https://dedupedai.com/use-cases/surya-koritala-glyd/",
 "use_case_count": 4,
 "use_cases": [
  {
   "id": "surya-koritala-glyd--run-qwen35-9b-on-24gb-gpu",
   "title": "Run Qwen3.5-9B on a 24 GB GPU with long context",
   "best": true,
   "url": "https://dedupedai.com/use-cases/surya-koritala-glyd/run-qwen35-9b-on-24gb-gpu/",
   "json": "https://dedupedai.com/use-cases/u/surya-koritala-glyd/run-qwen35-9b-on-24gb-gpu.json"
  },
  {
   "id": "surya-koritala-glyd--serve-qwen35-9b-with-vllm",
   "title": "Serve Qwen3.5-9B through vLLM with Glyd quantization",
   "best": false,
   "url": "https://dedupedai.com/use-cases/surya-koritala-glyd/serve-qwen35-9b-with-vllm/",
   "json": "https://dedupedai.com/use-cases/u/surya-koritala-glyd/serve-qwen35-9b-with-vllm.json"
  },
  {
   "id": "surya-koritala-glyd--load-bf16-model-in-python-with-glyd",
   "title": "Load a bf16 model in Python with Glyd",
   "best": false,
   "url": "https://dedupedai.com/use-cases/surya-koritala-glyd/load-bf16-model-in-python-with-glyd/",
   "json": "https://dedupedai.com/use-cases/u/surya-koritala-glyd/load-bf16-model-in-python-with-glyd.json"
  },
  {
   "id": "surya-koritala-glyd--compress-json-event-files-with-glyd",
   "title": "Compress JSON event files smaller than zstd -3",
   "best": false,
   "url": "https://dedupedai.com/use-cases/surya-koritala-glyd/compress-json-event-files-with-glyd/",
   "json": "https://dedupedai.com/use-cases/u/surya-koritala-glyd/compress-json-event-files-with-glyd.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."
}