Ctrl Stack

Not chasing every new model. Running local AI for real work on a 7-year-old desktop.

[Ctrl Stack @ctrl_stack]

Unplugged my old PHP server the morning PHP2Shell dropped. This week my local model and I finally patched it.

Plot twist: it was already patched. My distro had backported the fix. php -v doesn't tell you that. The package changelog does.

So we called it done. Then I asked "are we actually done?" and it got worse:

- The TLS cert had been expired for five weeks. Renewal ran the whole time and failed every time, because the dynamic DNS record was dead. Nobody noticed, including me.
- Even with DNS fixed, it would have kept failing. My own firewall only allowed 80/443 from the LAN, so every Let's Encrypt packet would have been dropped.
- The weekly backup never ran. Not once. A stray character I typed into the cron file made cron ignore the whole thing. Every backup I had was one I'd run by hand.
- 11 old .bak files were sitting in the webroot, serving source code to anyone who asked.

None of that showed up on the first pass. It showed up from a restore drill instead of a file listing, a live probe page instead of php -v, and one more round of "what did we miss?"

All of it on a 7-year-old desktop with a 16GB card. Local model, my existing SSH keys, nothing sent to the cloud. That box has no business doing this, but it does it anyway.

[Ctrl Stack @ctrl_stack]

@0xSero Oh I thought you were building your own data center. Apologies if I misunderstood.

[Ctrl Stack @ctrl_stack]

@ashxhart Do you have numbers for this on a 5060Ti? I'd love to help contribute and bench it for you. Custom kernel, so maybe it won't port to a 5060?
Regardless, super impressive and congrats! 🫡

[Ctrl Stack @ctrl_stack]

@Letstalkparsiq @norsyx My hat is off to you for having the capital for 2x RTX 6000s and that much RAM. That's some serious cash and power in a single box. Someday I hope to have even 1x RTX 6000, but I have my doubts. 😂

[Ctrl Stack @ctrl_stack]

@Kenson_Plays @HermesAgentTips The most reliable method to run locally on my 5060Ti is using Strata by @coldniko. Running Qwen 3.8-flash-next IQ3_XXS at ~50-60 tok/s.
Needs about 45GB of my 64GB system RAM. But it's been a powerhouse and I couldn't be happier!

[Ctrl Stack @ctrl_stack]

I'm running on a 7 year old desktop, only new hardware is a 5060Ti 16gb. My main use case is a personal wiki. End of each day I record a voice memo of what I accomplished, blockers, in progress, up next, etc.
Helps me decompress and frees up my mind to think about the rest of life without trying to keep track of all my work projects and notes.
Using Strata with Qwem 3.8-flash-next. Absolutely loving it!

[Ctrl Stack @ctrl_stack]

@ItsmeAjayKV Strata and Qwen 3.8-flash-next has already unlocked "frontier" level intelligence on my 7-year old desktop. Granted, "frontier" from ~10 months ago. But Opus 4.6 was groundbreaking at one point. Now it's obsolete... amazing how tech rapidly advances.

[Ctrl Stack @ctrl_stack]

@Hikari_07_jp The waiting is killing me. And probably everyone else too. 😂

[Ctrl Stack @ctrl_stack]

@hotdropfps Ryzen 7 3700X & 5060Ti 16GB

[Ctrl Stack @ctrl_stack]

@coldniko Let's go! Qwen 4 here we come!!!

[Ctrl Stack @ctrl_stack]

@coldniko @UnslothAI So excited to try these later today! Been running Swift IQ3_XXS as my go-to, but these I have to try out! 🤜🤛

[Ctrl Stack @ctrl_stack]

Yeah I can only imagine.
I'd be thrilled with a second computer that can just do what my current 7 year old desktop can. But to re-build my current desktop would be between $2,400 and $3,200 (I had Grok try to find my parts list from 7 years ago).
And at that price, why buy 7 year old hardware? Just spend another $3k-$5k and get a GB-10 or a dual 7900/3090 build.

[Ctrl Stack @ctrl_stack]

@coldniko @Palinoema I switched to the GUI when it came out, but it sounds like the TUI is better for now? Absolutely love Strata and what it enables me to do. Still trying to figure out the best way to use it though. 🫡

[Ctrl Stack @ctrl_stack]

What model are you using in Strata? I have the exact hardware you're talking about and I'm very happy with the tok/s speeds. I'm running Qwen 3.8-flash-next Swift IQ3_XXS and getting between ~50 and ~65 tok/s during my work.

I know it's not super fast, but on a budget it's at frontier levels from the beginning of the year.

I'd love to know what work you're doing to see if I can help provide additional testing numbers! 🇯🇵🤜🤛🇺🇸

[Ctrl Stack @ctrl_stack]

@tmaiaroto @net_termina Oof. I haven't checked ebay in a few weeks so that doesn't surprise me. 😅

[Ctrl Stack @ctrl_stack]

@chimolog7 Thank you, I was wondering why my Strata downloads were slower than other models I pulled. Getting this configured now! 🤜🤛