0.8B browser demo
The model downloads from Hugging Face and runs on your device through WebGPU. Your questions and screenshots are processed in this browser. No sign-in, inference API or local server is needed.
A browser workspace for JEE Main and Advanced. Bring a question, follow the working, and check the result. Explore the models, mistakes, and experiments behind it.
Live demo: Qwen 0.8B9B browser export pendingModel details ↗
Exploratory output from a small browser model. Check every scientific step before relying on it.
No account. No API key. No local server.
One-time download of roughly 850 MB. Requires WebGPU and enough device memory. We do not upload your question to our server; model files come from Hugging Face.
The solver is a research preview. It can make confident mistakes, especially on Advanced multi-step questions.
Choose with the full picture: the current browser demo and the trained 9B archive serve different purposes.
The model downloads from Hugging Face and runs on your device through WebGPU. Your questions and screenshots are processed in this browser. No sign-in, inference API or local server is needed.
The unchanged 9B base and experimental adapters used MLX on a Mac. The adapter conversion to PEFT passed small native parity checks. A verified Transformers.js export is still missing.
View the actual adapter archive ↗Before enabling 9B here, we need browser-compatible weights, checks that the adapter is active, matched text and image outputs, and measured device memory. Publishing the page alone does not complete that work.
Read the export status ↗A browser-side structure around the model, designed for readable work rather than a bare answer.
Subject, exam, expected answer type and possible thermodynamics sign conventions become explicit before generation.
The prompt asks for givens, a short subgoal plan, essential calculations and all requested branches.
The page checks requested sections and runs a separate calculation for one simple kinematics pattern. Other mathematical steps remain unverified.
This first browser harness does not yet have a general symbolic checker or calculator. Those are research tasks, and the 9B MLX adapters cannot be loaded by Transformers.js as-is.
The 9B training work and this browser demo are separate experiments. The archive shows the actual checkpoints and what each taught us.
Our latest controlled studies changed training families and LoRA layer coverage. Some outputs improved, others regressed; none passed the full selection rule.

