HackerTrans
TopNewTrendsCommentsPastAskShowJobs

andreinwald

no profile record

Submissions

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

andreinwald.github.io
145 points·by andreinwald·12 bulan yang lalu·54 comments

comments

andreinwald
·12 bulan yang lalu·discuss
It works on small Llama-3.2-1B model, specially for less powerfull GPU devices
andreinwald
·12 bulan yang lalu·discuss
Model used: Llama 3.2 1B (small). Quality hould be similar with running Ollama app with same small model.
andreinwald
·12 bulan yang lalu·discuss
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 bulan yang lalu·discuss
Yes, its very similar to Ollama app, and Llama-3.2-1B model used
andreinwald
·12 bulan yang lalu·discuss
Llama 3.2 1B
andreinwald
·12 bulan yang lalu·discuss
Also here https://caniuse.com/webgpu
andreinwald
·12 bulan yang lalu·discuss
Demo site is asking before download