Every model SecureRAG downloads, listed with its size and licence
Five model files exist in total, all of them open-licensed and small. Two cover almost everyone at roughly 25 MB each, and the two generative models are optional downloads you never have to press. This page gives the numbers.
Last updated:
Nothing here is fetched when a page loads. A model file is downloaded once, after you press a button that names the file and its size, and it is stored in your own browser cache. After that the whole application works offline.
All five model files in one table
| Model | Parameters | Quantisation | First download | Vector dimensions | Languages | Licence | Source |
|---|---|---|---|---|---|---|---|
| bge-small-zh-v1.5 — default for Chinese | ≈ 24 M (listed as 0.02 B on the model page) | int8 dynamic quantisation, ONNX | ≈ 25 MB | 512 | Chinese; short English text works but retrieves worse | MIT, as stated on the model page | https://huggingface.co/Xenova/bge-small-zh-v1.5 |
| all-MiniLM-L6-v2 — default for English | ≈ 23 M | int8 dynamic quantisation, ONNX | ≈ 23 MB | 384 | English | Apache-2.0, as stated on the model page | https://huggingface.co/Xenova/all-MiniLM-L6-v2 |
| multilingual-e5-small — optional, mixed-language documents | ≈ 118 M (0.1 B on the model page) | int8 dynamic quantisation, ONNX | ≈ 120 MB | 384 | Over 100 languages; the pick when one library mixes Chinese and English | MIT, as stated on the model page | https://huggingface.co/Xenova/multilingual-e5-small |
| Qwen2.5-0.5B-Instruct — optional, writes answers | 0.49 B total, 0.36 B excluding embeddings | 4-bit weight-only quantisation | ≈ 400 MB | Not applicable; it produces text, not search vectors | 29+ languages, Chinese included | Apache-2.0, as stated on the model page | https://huggingface.co/Qwen/Qwen2.5-0.5B-Instruct |
| Qwen2.5-1.5B-Instruct — optional, writes answers | 1.54 B total, 1.31 B excluding embeddings | 4-bit weight-only quantisation | ≈ 1.0 GB | Not applicable | 29+ languages, Chinese included | Apache-2.0, as stated on the model page | https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct |
Hardware, and what WebGPU changes
Embedding runs on a Web Worker, so the interface stays responsive while a document is indexed. When your browser exposes WebGPU, that worker runs the model on the graphics chip; when it does not, the same model runs through the WebAssembly build of onnxruntime that ships with the site, on the CPU. The CPU path is several times slower, and on a long PDF the difference is a few seconds against a minute. No feature is missing on the CPU path — it is the same embeddings and the same results.
| Setup | Retrieval and embedding | The optional 1.5B generation tier | What we suggest |
|---|---|---|---|
| Desktop with WebGPU (Chrome, Edge, recent Safari) | Runs on the GPU, several times faster than the CPU path | Turns over a few words per second — readable, well behind a cloud chatbot | The intended setup. 300 MB of free memory is enough for retrieval only |
| Desktop without WebGPU (Firefox, older Safari, older GPUs) | Falls back to the WebAssembly build bundled with the site | Slow. Fine for one short paragraph, tedious for a long answer | Use the retrieval-only tier here; it is fully functional |
| Phone or tablet | Works, with lower collection limits and a memory ceiling the mobile browser enforces | Off by default: the download is larger than a mobile tab is usually allowed to hold | Good for looking things up. Indexing a long report is better done on a computer |
| Browser without WebAssembly, or with storage for the site disabled | Not supported | Not supported | We say so on the first screen rather than fail halfway through indexing |
The 30 MB rule, and how a download is confirmed
The default embedding models are under 30 MB and cover most libraries. Four things are heavier than that: the multilingual embedding model at about 120 MB, and the two generation models at roughly 400 MB and 1.0 GB. Any of the four is offered, never imposed, and each purchase of your bandwidth is confirmed twice: once when you open the download panel, once when you press the button.
The panel states the cost first
Before a single byte moves, the panel shows the model name, the exact file size, the host it will be fetched from and the licence it carries. Nothing is requested while you read it.
You press a button that names the size
The action reads like “Download 120 MB”, not “improve my results”. Closing the panel instead cancels the whole thing, and no request was sent.
Progress is visible, and cancelling is real
You see transferred bytes while the file arrives. Cancelling mid-download throws away the partial file rather than leaving a half model on disk.
The file is stored in your browser, and asked for once
It lands in Cache Storage under your browser profile. The same file is not requested again unless you clear site data, or the browser evicts it under storage pressure — in which case the panel appears again with the same figures.
What the request contains
- A file name and a revision reference in the URL, and nothing else.
- No query string carries your document, your question, your language or any identifier we could use to recognise you.
- No cookie is attached, because there is no account system to set one and the request is made without credentials.
- The model host sees your IP address, as any site you visit does. That is a property of the open internet, not something this application adds.
- If the primary host is unreachable, the same file may be fetched from a mirror. The file name, the model and the size stay identical, and it is the same request shape.
Check the download figures yourself
- Open the tool, then open DevTools and go to the Network tab. Tick “Preserve log” and set the filter to all requests.
- Clear the request list, then add a document. Nothing new appears.
- Switch the model tier. Open the download panel and read the size before confirming — the number there is the number in Table 1.
- Press the download button and watch the single request: the path carries the model file name, the response is the file itself, and the transfer size rounds to the figure in the table.
- Go to the Application tab → Cache Storage. The model is there. Your document is not in that cache; chunks and vectors sit in IndexedDB.
If something here turns out to be wrong
Tell us at guweiicy@gmail.com, with the model name and the figure you checked. A licence or parameter count that contradicts the upstream model page is a mistake on our side, and we correct it and note the change on the changelog.