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·il y a 12 mois·54 comments

comments

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