News for hackers. Stuff that matters.
Re:Web LLM – WebGPU Powered Inference of Large Language Models by quickthrower2 on Sunday April 16, 2023 @08:34AM (#35589467)
Works well on my Dell XPS13 which is not particularly powerful but is modern. Answers are slower than chatGPT but not painfully slow and the response quality is great.
Re:Web LLM – WebGPU Powered Inference of Large Language Models by tuukkah on Tuesday April 18, 2023 @08:40AM (#35613202)
What's the GPU in your model?