Hetzner is working on LLM Inference

jjonas_scholz about 3 hours ago 22 commentsRead Article on sliplane.io

HI version is available. Content is displayed in original English for accuracy.

⚡ Community Insights

Discussion Sentiment

88% Positive

Analyzed from 601 words in the discussion.

Discussion (22 Comments)Read Original on HackerNews

rebelde•3 minutes ago

Hetzner is very efficient hosting servers

Will this be the new division of labor?

Americans - best proprietary models

Chinese - best open weight models

Europeans - best / most efficient inference service

swiftcoder•about 1 hour ago

It would certainly be interesting to have a highly respected EU-native inference provider, if only to make the regulatory gods happy

hoppp•10 minutes ago

Scaleway does that already but competition is always good.

jonas_scholz•about 1 hour ago

agree. I have a usecase for a bigger open-weight model hosted by an EU company and the selection isnt really great, hard to make the regulatory gods (and the devs) happy at the same time right now

sofixa•about 1 hour ago

Scaleway have two separate (one fully managed one a bit less) services for that:

https://www.scaleway.com/en/generative-apis/

https://www.scaleway.com/en/inference/

jonas_scholz•about 1 hour ago

yea, but no prompt caching right? This makes it unusable for my usecase at least, the cost would be insane

ano-ther•about 2 hours ago

Good to see more developments in this space. I quite like this service, which is a little further than Hetzner and has several models to choose from: https://www.infomaniak.com/en/hosting/ai-services

drcongo•9 minutes ago

Important note on Infomaniak's offering - when they first launched it, I gave it a try but despite claims that it's OpenAI API compatible, even basic things like sending a base64 encoded image were broken. I reached out to their support, who replied with (verbatim): "Unfortunately, we do not provide support for our AI Service, as the solution is highly unmanaged and uses our API."

"highly unmanaged" didn't fill me with confidence, and "uses our API" is a very weird reason to give for not offering support. I wrote off ever using them for anything beyond email after that reply.

jonas_scholz•about 2 hours ago

Interesting, didn’t know about them! Weird model selection though, no glm or deepseek?

archerx•about 2 hours ago

Infomaniak is such a shitty company, I had to use them on a previous job I worked at and dealing with them was awful.

MASNeo•about 1 hour ago

That makes it sound like dealing with Hetzner is easy. Is the case?

sam_lowry_•17 minutes ago

Depends on your mindset. If you are an Engineer that does not need hand-holding and you accept terse answers from support with the gratitude to the human on the other side, then go for it.

You will at least not need months of training and tough exams to be an expert in Hetzner Cloud. It is simple, but that's the point.

mark_l_watson•about 1 hour ago

This seems like a smart move, given their ability to host efficiently. I approve of efforts to make the cost of inference for smaller useful models slowly approach 'close to zero' and there are many good paths for getting there. It is useful for companies to get fast hosting for the class of smaller models they may end up hosting in house.

jonas_scholz•about 1 hour ago

I really hope they dont stop at the small models though! The bigger ones that dont fit on a single GPU are more interesting I think

embedding-shape•about 2 hours ago

> The enable_thinking option is worth mentioning. Without it, the model can spend a surprising amount of the completion budget reasoning before it returns a visible answer.

Straight up the opposite, which the name makes abundantly clear, with the option it does reasoning, without it it doesn't...

jonas_scholz•about 1 hour ago

My writing wasnt clear here I think, without the option it defaults to reasoning enabled. With "without it" I meant without enable_thinking=False!

cyanydeez•about 1 hour ago

llamacpp has a reasoning-budget and reasoning-message setting that can both be a global or per header setting. Using it, you can stop it's reasoning token count and insert a message at the point you stopped it.

This allows both the client and server to customize it. I typically use a message that tells it to compact the conversation and use subagents. I find the reasoning gets bloated when it's failed to do whatever task it's doing and often times it either has too little context (subagents) or its context is bloated (compact).

This works fairly well to get it to extend workable life up to ~1M on a local model.

nubg•22 minutes ago

Potentially interesting article ruined by AI slop hallucinations like

> For now, the API is fast, free, and fun to try. The next hardware announcement will tell us much more than another small model would.

jonas_scholz•18 minutes ago

what is the hallucination here? it is fast, free and fun to try. And I genuinely think that the hardware decision (if they get bigger gpus) decides if this will be a banger product or not?

nubg•3 minutes ago

nobody writes like that. the article is based on a prompt, which i would much rather read, instead of the ironed out version that the llm produced

jonas_scholz•1 minute ago

fine, i agree that this doesnt sound like me. But the content is correct and not a hallucination!