{
 "repo": "mlc-ai/web-llm",
 "url": "https://github.com/mlc-ai/web-llm",
 "what": "WebLLM is an in-browser LLM inference engine that runs models such as Llama 3, Phi 3, Gemma, Mistral and Qwen entirely on the user's device with WebGPU, with no server. It exposes an OpenAI compatible chat completions API with streaming and JSON mode, and supports Web Workers, Service Workers and Chrome extensions.",
 "language": "",
 "stars": null,
 "gain": null,
 "created": "",
 "uc_n": 3,
 "title": "Web LLM",
 "show": true,
 "what_source": "deduped",
 "use_cases": "https://dedupedai.com/use-cases/mlc-ai-web-llm/",
 "use_cases_json": "https://dedupedai.com/use-cases/r/mlc-ai-web-llm.json",
 "json": "https://dedupedai.com/repos/r/mlc-ai-web-llm.json",
 "slug": "mlc-ai-web-llm",
 "api": "https://dedupedai.com/api/v1/repos/mlc-ai-web-llm.json",
 "api_version": "v1"
}