DGX Spark is really poor at inference due to the memory bandwidth so hopefully they’ve fixed that before touting this as a way to run local models.

I think DGX Spark has poor memory bandwidth because these laptops were the plan all along. NVIDIA didn't want to commit to the extra costs of a 512-bit memory bus for their first laptop SoC, so they went with the more modest 256-bit bus, same as AMD did for Strix Halo.

> Only downside is the Search on mobile. You have to install an app and enable it as extension on safari. Logging in never worked and couldn't enable my premium Kagi on iPhone.

I just have Kagi set a custom search engine in mobile browser - no seperate app needed.

https://kagi.com/search?q=%s

Unfortunately the only way to do it on IOS Safari is as the user above described, you have to install and configure an extension, there are no 'custom' search engines natively. Other IOS browsers are fine, i.e. Chrome, Vivaldi, Orion, etc.

You're right, I use Brave on iOS but Safari doesn't let you choose beyond a defined list.

+1 for Kagi. Been a subscriber for almost 2 years and no intention of cancelling, it just works.

Solved !== Good

This is exactly my experience of working in an agency. Made worse by Figma defaulting to 1440px so every design only really works at that width.

It’s just gambling without the stigma of being called an addict.

Love what you guys have done with Unsloth. Any plans to have this running as a hosted product where Unsloth provide the GPUs?

Thank you! Great idea - that is actually one of the follow up goals! We know some folks want to do large scale training runs or inference with large models so the next most natural thing is to provide an API for folks and also provide infrastructure ourselves!

> These days I hit the quick answer button inside Kagi more often

Just incase you didn’t know you can append ? to any query and get a quick answer straight away

Actually, I didn't know. Thanks!

This may help you work out the best quant to use for your use case.

https://www.siquick.com/blog/model-quantization-fine-tuning-...

Sure sounds like automatic weapons targeting using Anthropic models to me.

However much they try to make us think otherwise, at this point in time there’s not really any “good guys” in the AI race.