Runs in the browser · Multimodal (any-to-any)
Run Janus-Pro-1B in your browser
Janus-Pro-1B downloads 1.81 GB over WebGPU (q4f16), or 2.11 GB over WebAssembly (uint8), to both understand and generate images from one checkpoint entirely in the tab with Transformers.js. No install, no server.
Multimodal (any-to-any) · onnx-community/Janus-Pro-1B-ONNX
- Parameters
- 2.08B
- Pipeline task
- custom
Reading
Janus-Pro does both image understanding and image generation from one checkpoint; there is no stable transformers.js pipeline() task for that yet, so expect custom wiring. This is a multi-gigabyte download. Between the file size and current browser memory limits, it is impractical to run on most machines today.
0.89 MB/M params against a 0.63 MB/M multimodal (any-to-any) median: dense for its parameter count.
The quant ladder spans 4.7x: 1.81 GB (q4f16) to 8.42 GB (fp32).
Will it run in your browser?
Checking for WebGPU support…
All measured variants
| Variant | Size |
|---|---|
| q4f16 WebGPU pick | 1.81 GB |
| uint8 WASM pick | 2.11 GB |
| bnb4 | 2.68 GB |
| q4 | 2.78 GB |
| fp16 | 4.21 GB |
| q8 | 4.23 GB |
| fp32 | 8.42 GB |
Sizes measured from the HuggingFace API file tree for onnx-community/Janus-Pro-1B-ONNX, not estimated.
Use it with Transformers.js
There is no stable transformers.js pipeline() call for this model yet, and no verified low-level snippet either (see the Reading panel above). Check the model card on HuggingFace for current usage examples.
Sources
Same job, different size
FAQ
WebGPU or WASM for Janus-Pro-1B, in practice?
Chrome, Edge, and Safari 26+ run the WebGPU build (q4f16) on the GPU. Firefox has WebGPU on Windows and Apple Silicon Macs but not everywhere yet. Any browser without a WebGPU adapter falls back automatically to the WebAssembly build (uint8) on CPU: same model, slower to load, slower to run.
What does q4f16 mean for Janus-Pro-1B?
The WebGPU build here uses q4f16: 4-bit weights with some layers kept at 16-bit for stability: WebGPU's usual smallest clean build. The WASM fallback uses uint8: 8-bit integers: about a quarter the size of fp32, with a smaller quality trade than 4-bit.
Sizes measured 2026-08-01 from the HuggingFace API. Last validated 2026-08-03. See all browser models or the methodology.