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)→
More from Infra
- 200 tok/s on 8GB VRAM: dev benchmarks 6 small models for local AI — TheMoonMidas · 2026-09-06
- Huawei Chief Scientist Details Logic Folding Cooling: Density Near TSMC N3E Level — teortaxesTex · 2026-09-06
- M5 Max user gets ~20 tok/s running DeepSeek locally, asks which open models to pick — A_Wild_Entei · 2026-09-06
- Ampere Public grants free access to ~1,000 interconnected chips for two-day research projects — charliermarsh · 2026-09-06
- Kimi and MiniMax to open Tmall stores selling token plans; Xiaomi releases table-data LDM — 创业邦 · 2026-09-06
- AMD exec: AI token processing could hit 120 quadrillion per month by 2030 — zephyr_z9 · 2026-09-06