What downloads
Public files, stored by your browser.
The model weights, tokenizer, configuration, and browser runtime assets are fetched when requested. Your input is not attached to those file requests.
RunnableEmbeddings · q8
all-MiniLM-L6-v2 · quantized
Turns two English passages into normalized 384-dimensional vectors and compares their semantic similarity.
Runtime facts
Know what will run before it downloads.
Run Any AI uses the public browser-ready model and exposes the important runtime choices. No Run Any AI backend receives the lab input or output.
- Model ID
- Xenova/all-MiniLM-L6-v2
- Task
- Embeddings
- Runtime
- WebAssembly
- Accelerator
- CPU
- Quantization
- q8
- Language
- English
- License
- Apache-2.0
- AI API key
- Not required
Use with care
Known limitations
- Similarity is a mathematical signal, not proof that two statements have the same meaning.
- Long passages are truncated to the model context limit.
- Thresholds must be validated for the intended search or duplicate-detection task.
Test the model with representative data before relying on its output in a real workflow.