In the Netherlands there is a computer museum with a huge collection. The computers can be used by anyone. Really a great experience for kids these days and adults.

https://www.homecomputermuseum.nl/en/

Conveniently located in outer Eindhoven!

I use Whisper in combination with Qwen3.8 27b to create Dutch subtitles for Russian videos. I follow Ukrainian channels about the war and I am now able to understand them. In my tests with other languages Voxtral was better then Whisper. Whisper often makes mistakes which I now solve with an extra layer (qwen).

Sadly Mistral does not support Ukrainian. I hope this changes! I expect better from a European model

On the DGX I get 44.5 tokens per second (NVFP4). With 8 concurrent it's 241 t/s total.

I am using the PrismaAQUA

standard 9.7 t/s

+ Dflash2 30 t/s

+ torch-compile 37 t/s

c8 = 177 t/s

What model? Also, I don't know what "the PrismaAQUA" means, ddg thinks it's a CPAP machine, which seems unlikely to help with inference performance.

Also, 4-bit has measurable intelligence loss. Sometimes worth it, but, at this size models are barely smart enough at 8 or 6.

Qwen3.8-27B-PrismaAQUA-5.5bit-vllm

The output quality is higher. It's held at full precision (not quantized).

This should have been the link!

https://pplx-dgx-spark-lp-demo.pplx.app/

Looks very useful

update:

It advertises with local harness and models but its closed source and you need a pro or max account

Very unclear what the value proposition is, when there are already other great open harnesses evolving at increasing speeds.

I agree. A better approach would be to have everyone access the harness for free, make it open source, when more resources are needed move the workload to Perplexity for a fee.

Intel did some promising deals (dc, Europe, arc gpu) but still no real answers to AMD and Nvidia. I pulled out from Nvidia, MSFT and Intel and ramp up AMD. Too much happening for me in the AI space and miss the base that Intel used to have.

I use it for a while now. One thing that is super frustrating is that it saves it data (prompts etc) to the cache folder instead of applications data. Cache obviously can be deleted by the OS when disk space is limited or when there is a cleanup. I had to start over many times because of this. Also there is no way to report bugs bug for Spotify Studio.

what are you using it for? Whats the single best use case?

It creates a hyper personal daily podcast with latest niche news which is interesting for me alone. And it does that pretty well.

You can probably create it yourself using an LLM, search and Elevenlabs.

I wouldn't describe it as luck, it's politics. The mother of Bill Gates had access to the board of IBM. She was also the co-founder of Microsoft.

That is just an amazing website and initiative.

https://rvembedded.com/products/project-lab/

Definitely interested!

It's not just the AI. The post mentions poor choices because of a product management mindset instead of engineers leading the PMs.

Only part of the article I disagree with a bit. I'm willing to bet most infrastructure PM's at CF are technical people with engineering backgrounds.

I think what's more likely the culprit is the desperation to claim ground. They (and many others) want to rush out an answer to all of AI's new challenges out of fear of being beaten to the punch.

It usually leads to a complex, almost incoherent product suite.

Great read. Exact pinpointing of my feelings about CF lately.