OpenJev in your browser (../fonts.googleapis.com/css2@family=Material+Symbols+Rounded%253Aopsz,wght,FILL,GRAD@20,600,0,0&icon_names=add,celebration,check,check_circle,download,error,hourglass_top,memory,play_arrow,progress_activity,refresh,remove,replay&display=block.css)  (style.css)   (index.html) openjev Can we run something like Jev in your browser? (https://github.com/TheoLeeCJ/openjev) GitHub repo ↗   A live, local experiment Decision model in your browser.  A local model can either read probabilities for your allowed options without decoding them, or write the same kind of distribution token by token. Pick a size, run both on your own GPU, and measure the difference. browser only no backend your timings 1.56 GB model  celebration There is no waitlist! Just try it out ↓  MiniCPM5 2B is selected by default. On a phone or smaller device, switch to Qwen3 0.6B in the model box if needed.  00 / setup Load the model once  Model (qwen3-0.6b) Qwen3 0.6B · recommended for phones and small devices (minicpm5-2b) MiniCPM5 2B · recommended on desktop (qwen3.5-4b) Qwen3.5 4B · high-memory desktop   download load MiniCPM5 2B   Larger model. Loading may be slower or may not fit on some low-end devices. Model performance higher is better  Model Download Authored Perturbed TypeSafe   Qwen3 0.6B 639 MB 44.0% 52.8% 40.7%  MiniCPM5 2B 1.56 GB 68.6% 69.3% 63.7%  Qwen3.5 4B 3.01 GB 81.3% 76.6% 84.5%  Published Jev hosted — — 88.3%     Native BF16 · TypeSafe: same 102-row subset · Jev: published result · browser builds are quantized  {{ icon }} {{ text }}  download / cache —   starts only when you click load  model load — download and prepare  warmup — compile passes for both methods   Weights come from Hugging Face and remain in your browser cache. Inputs never leave this page. First load can take several minutes depending on the selected model, network and GPU.  01 / decision Give it a real choice  play_arrow run both methods  Try an example Account support Email triage  StateA customer says a password reset succeeded, but every login attempt still returns “account locked”. Two unlock emails were requested and neither arrived.  Question(Which queue should handle this request?)   Allowed options A (Account access support)   B (Billing support)   C (Close as resolved)    remove remove 3 / 20 add add    Both paths receive the same decision. One reads option probabilities directly; the other asks the model to write its option probabilities as JSON text.  your decision state + question + options  → same local model MiniCPM5 · 2B  ↗ ↘ read logits A…T probabilities  write tokens { options +  probabilities }     02A / direct readout Choice probabilities  no decoding  Read the model’s choice logits and normalize only across the options you supplied. waiting for a run total —  input —  output 1 readout    02B / generation JSON probabilities  token by token  Ask the model to estimate the same displayed-option distribution and write it as JSON. Watch every token arrive. waiting for a run first token —  total —  input —  output —     measured wall-time ratio run it on your GPU The methods run sequentially on the same loaded model so they do not contend for one GPU. Direct runs first, then generation.  What these numbers do—and do not—mean Conditional probabilities. Direct scores are a softmax over only the displayed option tokens. They are not calibrated confidence and do not include every answer the model might prefer. Local model tiers. The phone model trades accuracy for size. MiniCPM is the desktop default. The 4B option needs substantially more memory. None is claimed to match Jev. Real local timing. Setup, warmup, prompt preparation, direct execution, first generated token and generation completion are timed with performance.now() . No canned results appear. Quantized weights. The demo uses pinned GGUF builds through wllama. Quantization can change both quality and speed.   OpenJev / browser lab (https://github.com/TheoLeeCJ/openjev) GitHub repo · (https://huggingface.co/openbmb/MiniCPM5-2B-GGUF) model · (https://github.com/ngxson/wllama) wllama