[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-73599":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":11,"languages":10,"totalLinesOfCode":10,"stars":12,"forks":13,"watchers":14,"openIssues":15,"contributorsCount":16,"subscribersCount":16,"size":16,"stars1d":16,"stars7d":17,"stars30d":18,"stars90d":16,"forks30d":16,"starsTrendScore":16,"compositeScore":19,"rankGlobal":10,"rankLanguage":10,"license":20,"archived":21,"fork":21,"defaultBranch":22,"hasWiki":23,"hasPages":23,"topics":24,"createdAt":10,"pushedAt":10,"updatedAt":25,"readmeContent":26,"aiSummary":27,"trendingCount":16,"starSnapshotCount":16,"syncStatus":28,"lastSyncTime":29,"discoverSource":30},73599,"smolvlm-realtime-webcam","ngxson\u002Fsmolvlm-realtime-webcam","ngxson","Real-time webcam demo with SmolVLM and llama.cpp server","https:\u002F\u002Fgithub.ngxson.com\u002Fsmolvlm-realtime-webcam\u002F",null,"HTML",5554,896,56,12,0,1,5,39.86,"Other",false,"main",true,[],"2026-06-12 02:03:15","# SmolVLM real-time camera demo\n\n![demo](.\u002Fdemo.png)\n\nThis repository is a simple demo for how to use llama.cpp server with SmolVLM 500M to get real-time object detection\n\n## How to setup\n\n1. Install [llama.cpp](https:\u002F\u002Fgithub.com\u002Fggml-org\u002Fllama.cpp)\n2. Run `llama-server -hf ggml-org\u002FSmolVLM-500M-Instruct-GGUF`  \n   Note: you may need to add `-ngl 99` to enable GPU (if you are using NVidia\u002FAMD\u002FIntel GPU)  \n   Note (2): You can also try other models [here](https:\u002F\u002Fgithub.com\u002Fggml-org\u002Fllama.cpp\u002Fblob\u002Fmaster\u002Fdocs\u002Fmultimodal.md)\n3. Open `index.html`\n4. Optionally change the instruction (for example, make it returns JSON)\n5. Click on \"Start\" and enjoy\n","该项目是一个基于SmolVLM和llama.cpp服务器的实时摄像头物体检测演示。它通过结合使用轻量级的SmolVLM 500M模型与高效的llama.cpp后端，实现了对摄像头捕捉图像中的对象进行即时识别，并能够根据用户定义的指令返回结果，支持GPU加速以提高处理速度。适用于需要快速部署视觉理解能力的应用场景，如智能家居安全监控、简易版AR体验开发等，尤其适合希望探索多模态大模型技术潜力的研究人员或开发者。",2,"2026-06-11 03:46:19","high_star"]