Qwen 3.5 in YOUR BROWSER (Setup Guide)

Qwen 3.5 now runs fully in the browser via WebGPU, but you still pay a ~8 GB download and slower tokens.

How it works

Eric's project loads the Qwen model directly into your GPU through the browser's WebGPU API. The creator stresses that this is only possible because modern browsers now have full GPU access — "back in the day" the browser couldn't reach VRAM, so this wasn't an option. No LM Studio, no llama.cpp, no Python environment.

The catch: the 3060 ceiling

The demo machine is a Windows PC with an NVIDIA 3060. That card has limited VRAM, capping usable models at ~8 GB or less. The 3060 "was meant for gaming" — "you only need it for your textures." A Mac with unified memory gets around this; Windows users don't. The creator is blunt: a 27B / 37B parameter Qwen build is an even bigger pull, and on his connection the download is painfully slow.

Performance target

The hard floor is ~30 tokens/second. Below that, "you're not going to wait for it" — a 1 tok/s model feels like "30 seconds per hey." Thinking models are worse because they burn tokens planning before replying. The Qwen thinking model on screen was visibly stalling during inference in the demo.

Privacy and cost angle

Local = nothing leaves your device. The creator pitches this directly at viewers worried about data leaving for China, and at anyone tired of paying for API credits. "You can do everything for free with your own graphics card."

Verdict from the creator

Browser is for experimentation and the lazy-installer crowd. For actual coding, vibe-coding, or running larger Qwen 3.5 variants (especially the Opus-Reasoning distilled one he's saving for the next video), run a local server. The browser path is a fun 2026 flex, not a daily driver.