HackerTrans
トップ新着トレンドコメント過去質問紹介求人

andreinwald

no profile record

投稿

Show HN: WebGPU enables local LLM in the browser – demo site with AI chat

andreinwald.github.io
145 ポイント·投稿者 andreinwald·12 か月前·54 コメント

コメント

andreinwald
·12 か月前·議論
It works on small Llama-3.2-1B model, specially for less powerfull GPU devices
andreinwald
·12 か月前·議論
Model used: Llama 3.2 1B (small). Quality hould be similar with running Ollama app with same small model.
andreinwald
·12 か月前·議論
On my Android device works pretty fast.

But keep in mind that it's small Llama-3.2-1B model, specially for less powerfull GPU.
andreinwald
·12 か月前·議論
Yes, its very similar to Ollama app, and Llama-3.2-1B model used
andreinwald
·12 か月前·議論
Llama 3.2 1B
andreinwald
·12 か月前·議論
Also here https://caniuse.com/webgpu
andreinwald
·12 か月前·議論
Demo site is asking before download