A place to post results / benchmarks, best setups, guides, result analysis, and performance questions. E.g. OpenAI, Gemini
Thanks and two questions:
One, what would be the appropriate thread for running small-enough Distills on mobile devices locally, i.e. on smartphones or tablets? There are some (IMHO) quite interesting attempts and even apps to make happen on Android and Apple.
Two, along similar lines, but also for PCs: Small Language Models. So, small enough to run on a laptop with an APU and maybe an NPU in the SoC. Which thread is the best one for that topic?
Thanks! I figured I ask first before either starting a thread for something that’s already there, or post it OT in a thread on LLMs.