Shimitar
@Shimitar@downonthestreet.eu
- Comment on cheap remote kvm 2 days ago:
I am using a GLiNET ip kvm. Small, great software. Has HDMI and USB, can be powered from USB itself too.
You can plug in files over the web interface like they are USB drives too. Can install tails ale and more plugins, can fake any monitor resolution you need…
Very pleased for the price tag. Never let me down.
- Comment on PSA: unattended-upgrades restarted nginx in the middle of my stream 4 days ago:
Yeah problem is when upgrades break stuff…
- Comment on PSA: unattended-upgrades restarted nginx in the middle of my stream 4 days ago:
Unattended upgrade?
Why? Specially on critical systems?
If you do such upgrades, schedule for a time you don’t use the system at very least …
- Comment on 'My own piece of the Internet: Part 1', a blog post discussing the process of getting an ARIN ASN and a /24 IPv4 block for their home setup 6 days ago:
Reverse proxy my friend…
Using one static IP per service feels so much like … 1990s…
… As well as owing a /24, I admit.
- Comment on PSA to Home Assistant users 6 days ago:
Not really, they are testing your passwords against have I been pawnd. I agree that transparency should apply here, and also an upfront question to skip.
But it’s not “unsafe” or a privacy breach per se. No password has actually been “sent” anywhere only a partial hash that is useless for accessing your home assistant.
- Comment on Is anyone self-hosting their own AI? 6 days ago:
Yes i do.
I esperiment a lot, but my stable setup is Qwen 3.8 27B Q6_K on my home server. Hardware is Ryzen 9 5950x with 64gb ddr4 and two old but effective NVIDIA RTX A4000 for a total of 32gb VRAM.
Qwen 3.8 is the best model I can run in terms of output quality. It can perform all tasks pretty well and it’s reasonably fast at 500ts prefill and 30/40ts processing. There are much faster models but honestly not as good.
I can also run gemma4 all on CPU, with no GPU at all.
The key point is having both GPU on pci-e CPU, not on chip set bridge, so I am using a PCI riser 8x8x to share the 16x slot between the two GPUs. Inference speed is unaffected, but prefill benefits immensely.
Software side, use llama.cpp on Linux, you get the best performance possible at the expense of a bit more complexity compared to other engines.
From a power consumption perspective, I tined down my CPU governor and maximum frequency, and also the GPUs maximum watts. At ide the system is around 80w. At peak, it’s about 280w with the limiters, and inference speed doesn’t suffer too much. Without limiters I can easily reach 650w.
- Comment on 1 week ago:
I bought it new, but of course you can repurpose old hardware!
- Comment on 1 week ago:
I bought a firewall appliance based on an Intel CPU, with 4x 2.5gbps Ethernet ports, 8gb ram. Installed opnSense on it and been super happy even since!
A bit pricey the hardware, but it’s been totally rock solid for almost two years now.
- Comment on Self-hosted Radio 2 weeks ago:
What do you mean?
Who chooses the tracks?
Anyway yes, set a muted dj who never speak.
And create playlists and only play those. This will bypass any AI usage.
- Comment on Self-hosted Radio 2 weeks ago:
Subwave. A bit on the AI side… But it’s brilliant and really works great.
Only problem, you want to keep that private ad it’s most probably illegal anywhere to broadcast publicly without a license. Even on the internet
- Comment on Personal radio station 2 weeks ago:
Try subwave. You can have AI djs choose music from your navidrone library based on shows you create by defining prompts, moods and styles.
Pretty neat…
Fast developing and pretty solid already.