Vetted AI models that run on your device. Every file is an approved parameter file served once from models.skillsafe.ai — download it in one SkillSafe app and the next app already has it. Nothing you enter is uploaded to run it, and it never costs a credit. Models we convert ourselves are also published on Hugging Face — the same bytes with their provenance, for use outside SkillSafe. Missing one? Request it — or see how the registry works.
File type detection model for onnxruntime-web (fp32). Runs on WASM; 3.0 MB in one file, downloaded once and cached for every SkillSafe app.
Image segmentation model for onnxruntime-web (int8 dynamic-quantized). Runs on WASM; 13.1 MB in 2 files, downloaded once and cached for every SkillSafe app.
Image segmentation model for onnxruntime-web (fp16). Runs on WebGPU or WASM; 19.8 MB in 2 files, downloaded once and cached for every SkillSafe app.
Text recognition model for onnxruntime-web (fp32). Runs on WASM or WebGPU; 4.3 MB in one file, downloaded once and cached for every SkillSafe app.
Text detection model for onnxruntime-web (fp32). Runs on WASM or WebGPU; 1.7 MB in one file, downloaded once and cached for every SkillSafe app.
Background removal model for onnxruntime-web (fp32). Runs on WASM or WebGPU; 4.4 MB in one file, downloaded once and cached for every SkillSafe app.
Portrait matting model for onnxruntime-web (fp16). Runs on WASM or WebGPU; 12.4 MB in one file, downloaded once and cached for every SkillSafe app.
Text generation model for web-llm (q4f16_1). Runs on WebGPU; 2055 MB in 84 files, downloaded once and cached for every SkillSafe app.
Text generation library model for web-llm. Runs on WebGPU; 5.2 MB in one file, downloaded once and cached for every SkillSafe app.
Image to text model for transformers.js (q8). Runs on WebGPU or WASM; 479 MB in 2 files, downloaded once and cached for every SkillSafe app.
Image to text model for transformers.js (fp32). Runs on WebGPU or WASM; 914 MB in 2 files, downloaded once and cached for every SkillSafe app.
Image classification model for transformers.js (q8). Runs on WebGPU or WASM; 24.6 MB in one file, downloaded once and cached for every SkillSafe app.
Image classification model for transformers.js (fp32). Runs on WebGPU or WASM; 97.4 MB in one file, downloaded once and cached for every SkillSafe app.
Translation model for transformers.js (q8). Runs on WASM or WebGPU; 244 MB in 2 files, downloaded once and cached for every SkillSafe app.
Translation model for transformers.js (fp32). Runs on WASM or WebGPU; 404 MB in 2 files, downloaded once and cached for every SkillSafe app.
Image classification model for transformers.js (q8). Runs on WebGPU or WASM; 84.2 MB in one file, downloaded once and cached for every SkillSafe app.
Image classification model for transformers.js (fp32). Runs on WebGPU or WASM; 330 MB in one file, downloaded once and cached for every SkillSafe app.
Translation model for transformers.js (q8). Runs on WASM or WebGPU; 241 MB in 2 files, downloaded once and cached for every SkillSafe app.
Image super resolution model for transformers.js (fp32). Runs on WebGPU or WASM; 51.9 MB in one file, downloaded once and cached for every SkillSafe app.
Translation model for transformers.js (fp32). Runs on WASM or WebGPU; 398 MB in 2 files, downloaded once and cached for every SkillSafe app.
Object detection model for transformers.js (q8). Runs on WebGPU or WASM; 41.1 MB in one file, downloaded once and cached for every SkillSafe app.
Translation model for transformers.js (q8). Runs on WASM or WebGPU; 258 MB in 2 files, downloaded once and cached for every SkillSafe app.
Object detection model for transformers.js (fp32). Runs on WebGPU or WASM; 159 MB in one file, downloaded once and cached for every SkillSafe app.
Translation model for transformers.js (fp32). Runs on WASM or WebGPU; 425 MB in 2 files, downloaded once and cached for every SkillSafe app.
Translation model for transformers.js (q8). Runs on WASM or WebGPU; 258 MB in 2 files, downloaded once and cached for every SkillSafe app.
Translation model for transformers.js (fp32). Runs on WASM or WebGPU; 425 MB in 2 files, downloaded once and cached for every SkillSafe app.
Text2text generation model for transformers.js (q8). Runs on WASM or WebGPU; 191 MB in 2 files, downloaded once and cached for every SkillSafe app.
Text2text generation model for transformers.js (fp32). Runs on WASM or WebGPU; 357 MB in 2 files, downloaded once and cached for every SkillSafe app.
Token classification model for transformers.js (fp32). Runs on WASM or WebGPU; 411 MB in one file, downloaded once and cached for every SkillSafe app.
Feature extraction model for transformers.js (fp32). Runs on WASM or WebGPU; 449 MB in one file, downloaded once and cached for every SkillSafe app.
Text classification model for transformers.js (fp32). Runs on WASM or WebGPU; 256 MB in one file, downloaded once and cached for every SkillSafe app.
Automatic speech recognition model for transformers.js (q8). Runs on WebGPU or WASM; 486 MB in 2 files, downloaded once and cached for every SkillSafe app.
Automatic speech recognition model for transformers.js (fp32). Runs on WebGPU or WASM; 923 MB in 2 files, downloaded once and cached for every SkillSafe app.
Automatic speech recognition model for transformers.js (fp16). Runs on WebGPU or WASM; 463 MB in 2 files, downloaded once and cached for every SkillSafe app.
Automatic speech recognition model for transformers.js (q8). Runs on WebGPU or WASM; 60.7 MB in 2 files, downloaded once and cached for every SkillSafe app.
Automatic speech recognition model for transformers.js (fp32). Runs on WebGPU or WASM; 144 MB in 2 files, downloaded once and cached for every SkillSafe app.
Automatic speech recognition model for transformers.js (fp16). Runs on WebGPU or WASM; 72.6 MB in 2 files, downloaded once and cached for every SkillSafe app.
Automatic speech recognition model for transformers.js (q8). Runs on WebGPU or WASM; 130 MB in 2 files, downloaded once and cached for every SkillSafe app.
Automatic speech recognition model for transformers.js (fp32). Runs on WebGPU or WASM; 278 MB in 2 files, downloaded once and cached for every SkillSafe app.
Automatic speech recognition model for transformers.js (fp16). Runs on WebGPU or WASM; 139 MB in 2 files, downloaded once and cached for every SkillSafe app.
Depth estimation model for transformers.js (q8). Runs on WebGPU or WASM; 26.0 MB in one file, downloaded once and cached for every SkillSafe app.
Depth estimation model for transformers.js (fp32). Runs on WebGPU or WASM; 94.5 MB in one file, downloaded once and cached for every SkillSafe app.
Depth estimation model for transformers.js (fp16). Runs on WebGPU or WASM; 47.3 MB in one file, downloaded once and cached for every SkillSafe app.
Image classification model for transformers.js (q8). Runs on WebGPU or WASM; 84.4 MB in one file, downloaded once and cached for every SkillSafe app.
Image classification model for transformers.js (fp32). Runs on WebGPU or WASM; 329 MB in one file, downloaded once and cached for every SkillSafe app.
Text classification model for transformers.js (q8). Runs on WASM or WebGPU; 106 MB in one file, downloaded once and cached for every SkillSafe app.
Text classification model for transformers.js (fp32). Runs on WASM or WebGPU; 418 MB in one file, downloaded once and cached for every SkillSafe app.
Text ranking model for transformers.js (fp32). Runs on WASM or WebGPU; 271 MB in one file, downloaded once and cached for every SkillSafe app.
Feature extraction model for transformers.js (fp32). Runs on WASM or WebGPU; 416 MB in one file, downloaded once and cached for every SkillSafe app.
Text generation model for web-llm (q4f16_1). Runs on WebGPU; 2164 MB in 75 files, downloaded once and cached for every SkillSafe app.
Text generation library model for web-llm. Runs on WebGPU; 5.8 MB in one file, downloaded once and cached for every SkillSafe app.
Text generation model for web-llm (q4f16_1). Runs on WebGPU; 924 MB in 38 files, downloaded once and cached for every SkillSafe app.
Text generation library model for web-llm. Runs on WebGPU; 5.6 MB in one file, downloaded once and cached for every SkillSafe app.
Text generation model for web-llm (q4f16_1). Runs on WebGPU; 929 MB in 31 files, downloaded once and cached for every SkillSafe app.
Text generation library model for web-llm. Runs on WebGPU; 5.5 MB in one file, downloaded once and cached for every SkillSafe app.
Text generation model for web-llm (q4f16_1). Runs on WebGPU; 833 MB in 31 files, downloaded once and cached for every SkillSafe app.
Text generation library model for web-llm. Runs on WebGPU; 5.1 MB in one file, downloaded once and cached for every SkillSafe app.
Text generation model for web-llm (q4f16_1). Runs on WebGPU; 200 MB in 8 files, downloaded once and cached for every SkillSafe app.
Text generation library model for web-llm. Runs on WebGPU; 5.6 MB in one file, downloaded once and cached for every SkillSafe app.
Text generation model for web-llm (q4f16_1). Runs on WebGPU; 325 MB in 10 files, downloaded once and cached for every SkillSafe app.
Text generation library model for web-llm. Runs on WebGPU; 5.5 MB in one file, downloaded once and cached for every SkillSafe app.
Text generation model for web-llm (q4f16_1). Runs on WebGPU; 270 MB in 9 files, downloaded once and cached for every SkillSafe app.
Text generation library model for web-llm. Runs on WebGPU; 4.8 MB in one file, downloaded once and cached for every SkillSafe app.
Text to speech model for onnxruntime-web (q8). Runs on WebGPU or WASM; 115 MB in 56 files, downloaded once and cached for every SkillSafe app.
Text to speech model for onnxruntime-web (fp16). Runs on WebGPU or WASM; 183 MB in 56 files, downloaded once and cached for every SkillSafe app.
Feature extraction model for transformers.js (fp32). Runs on WASM or WebGPU; 448 MB in one file, downloaded once and cached for every SkillSafe app.
Feature extraction model for transformers.js (fp32). Runs on WASM or WebGPU; 127 MB in one file, downloaded once and cached for every SkillSafe app.
Feature extraction model for transformers.js (fp32). Runs on WASM or WebGPU; 86.2 MB in one file, downloaded once and cached for every SkillSafe app.
Background removal model for onnxruntime-web. Runs on WebGPU or WASM; 170 MB in one file, downloaded once and cached for every SkillSafe app.
Background removal model for onnxruntime-web. Runs on WebGPU or WASM; 168 MB in one file, downloaded once and cached for every SkillSafe app.
Background removal model for onnxruntime-web. Runs on WebGPU or WASM; 168 MB in one file, downloaded once and cached for every SkillSafe app.
Object detection model for onnxruntime-web. Runs on WebGPU or WASM; 34.2 MB in one file, downloaded once and cached for every SkillSafe app.
Object detection model for onnxruntime-web. Runs on WebGPU or WASM; 3.5 MB in one file, downloaded once and cached for every SkillSafe app.
Voice activity detection model for onnxruntime-web (fp32). Runs on WASM or WebGPU; 2.2 MB in one file, downloaded once and cached for every SkillSafe app.
Voice activity detection model for onnxruntime-web (fp16). Runs on WASM or WebGPU; 1.2 MB in one file, downloaded once and cached for every SkillSafe app.
Image super resolution model for onnxruntime-web (fp32). Runs on WebGPU; 63.9 MB in one file, downloaded once and cached for every SkillSafe app.
Image super resolution model for onnxruntime-web (fp16). Runs on WebGPU; 32.2 MB in one file, downloaded once and cached for every SkillSafe app.
Image super resolution model for onnxruntime-web (fp32). Runs on WebGPU; 64.0 MB in one file, downloaded once and cached for every SkillSafe app.
Image super resolution model for onnxruntime-web (fp16). Runs on WebGPU; 32.2 MB in one file, downloaded once and cached for every SkillSafe app.
Image super resolution model for onnxruntime-web (fp32). Runs on WebGPU or WASM; 17.1 MB in one file, downloaded once and cached for every SkillSafe app.
Image super resolution model for onnxruntime-web (fp16). Runs on WebGPU or WASM; 8.6 MB in one file, downloaded once and cached for every SkillSafe app.
Image super resolution model for onnxruntime-web (fp32). Runs on WebGPU or WASM; 2.4 MB in one file, downloaded once and cached for every SkillSafe app.
Image super resolution model for onnxruntime-web (fp16). Runs on WebGPU or WASM; 1.2 MB in one file, downloaded once and cached for every SkillSafe app.
Image super resolution model for onnxruntime-web (fp32). Runs on WebGPU or WASM; 4.6 MB in one file, downloaded once and cached for every SkillSafe app.
Image super resolution model for onnxruntime-web (fp16). Runs on WebGPU or WASM; 2.3 MB in one file, downloaded once and cached for every SkillSafe app.
Face detection model for onnxruntime-web. Runs on WASM or WebGPU; 224 KB in one file, downloaded once and cached for every SkillSafe app.
The registry is empty. Request the first model.