New on LowEndTalk? Please Register and read our Community Rules.
All new Registrations are manually reviewed and approved, so a short delay after registration may occur before your account becomes active.
All new Registrations are manually reviewed and approved, so a short delay after registration may occur before your account becomes active.
Comments
Funny, let's see if they deliver
Nothing since day 1
That's crazy
I can take it up if no one.
they delivered, i got it
What did you get ? yabs ..
You got something delivered today?
ks-le-3 yes with expired order. maybe i was lucky
Will they end up cancelling or will we see the real lotto hits start to be delivered? LE-6 with a better EPYC or even 256GB RAM?
@TomasSystems @neeoon
what do you ask me? Ask the Baguette seller @OVHcloud
AMD EPYC 8224P at least please
Got some stock LE-5 with 512gb nvme and LE-4 with 64gb ram and 2tb drives, if somebody needs them, else I'll have them refund soon.
So what is next ?
Black Friday 2027
Nothing, they will try to sell remaining which are less attractive and keep the attractive out of stock like always they do. And people will somehow take those less attractive because they have no other choice.
The product is being delivered
Which?
Baguette
Big city baguette
Actually the KS-LE-6 is amaze.
The Motherboard does support 8 Memory channels.
Since we are stuck at 128gigs, is just 4 but....
LLM's seem to kinda enjoy that bandwidth.
Usually after like 20k context the tps on a KS-LE-B goes down drastically
Here though 60k hold steady, I wonder if 128k would work as well.
what do you have running on it atm and how quick are we talking?
Im curious too.
Nobody talks about quick.
Its about keeping the initial tokens per second even on long context window.
Which makes it interesting, for long, agentic workloads.
Then it doesn't really matter if it takes longer right, at least for me.
I am running Qwen 3.8 Flash Next, newest unsloth 3bit quant.
I try 4bit later also 128k context.
3.8 Tokens per second, slow as fuck but stable.
thank you, thats handy to know.
Can you share your setup or maybe make small tutorial to run LLM(s) in KS-LE-6?
Install Proxmox, create a powerful VM, and give its SSH credentials to a capable AI model. It could be Opus 5.5 or Sol 6.2, or something similar. Ask it what it can do, explain what you want, and let it handle everything for you.
I would cry