what i could buy with 20-30€ costs over the hundreds
Khm-khm, arm boards, khm-khm
No like, for real, why 16gb arm board like O6 now costs almost 1k euro? 32gb version right now 1400 euro on aliexpress. FOR WHAT? Finest chinesium?
And “affordable” Raspberry Pi with as much ram as my toaster (and similar CPU at that) now costs more money, than regular small mini PC on x86.
You can use a DDNS
I need to dig into that a bit more, but I’m not sure if it will work with NAT on ISP side (with is a common thing at least in region I’m from).










Context limit is not really a problem on local models. Qwen3.6 can do up to ~256k tokens, it’s not that far from what things like cursor uses. grok in cursor have exactly 256k tokens for example. Also, you can use opencode with custom config, where you need to set trimming close to that number.
That being said, quality wise it still kinda shit and looses to paid models. I think you need something like GLM 5.2 to compete, which needs 228gb at lowest 1bit quant (not including context size, which can be up to 1m tokens, so you can round up requirements for RAM up to 256gb), so yeah, the only thing that limits you locally — the fact that “AI” companies bought all supply of focking ram and we can’t afford any.