Try it yourself: online demo of browser-based LLM fine-tuning via WebGPU

ngxson · x · 2026-09-06

ngxson shared the live demo link for the WebGPU fine-tuning PoC built on llama.cpp/wllama, letting anyone fine-tune an LLM directly in the browser. LoRA support is in progress.

Related event: WebGPU PoC Enables LLM Fine-Tuning Directly in Browser(2 posts)→

Original post →

More from Infra

Infra channel →