Local AI hardware, worked out
Aliteq computes VRAM from each model's own config and tracks live rental prices, so you can see what fits on your card, what it costs to run, and what to rent when it doesn't.
Lowest listed hourly price across Vast.ai and Runpod, updated 15m ago. Two providers tracked.
Local-AI hardware
Which card runs a model, what fits at your context length, and what it costs to rent — computed from each model's own config and live provider prices. Not opinion.
Olympiad golds, Erdős problems, a disproved 87-year-old conjecture and a better Riemann bound. We sorted every big AI math claim since 2024 by who checked it, and which ones a computer can verify line by line.
Aliteq Team · Oct 4 · 11 min
I mapped every Mac mini and Mac Studio Apple sells today, all 17 configs, against 13 popular local AI models. If your biggest model is 27B-class, the math says a $1,299 Mac mini holds what a $3,099 Mac Studio holds.
Aliteq Team · Oct 4 · 16 min
The one rule is buy VRAM, not benchmarks — and 2026's price surge is now cooling. My current, honest map: which card for which budget (Arc B580 to RTX 5090), what each actually runs, and when to rent or go unified-memory instead.
Aliteq Team · Aug 14 · 11 min
The RTX PRO 6000 nearly doubled in eight months. Here's what your money actually buys against every real alternative for running big models at home.
Aliteq Team · Aug 14 · 8 min
MSI just told investors gaming hardware prices are rising 15 to 30% this year, and the actual culprit is a DRAM shortage AI datacenters are causing, not GPU chips themselves.
Aliteq Team · Aug 13 · 6 min
AMD's own numbers put its workstation GPU at 53 tokens a second on Meta's new 30B model. Nvidia's flagship does more — for over three times the price.
Aliteq Team · Aug 11 · 6 min
Palo Alto Networks' Unit 42 pointed an ensemble of frontier AI models at almost 4,000 open source projects. 99.4% of what it found had never been reported before.
Aliteq Team · Aug 9 · 6 min
A Hong Kong shop is doubling old RTX 2080 Ti cards to 22GB of VRAM and selling them on eBay for about $500. I ran the actual math on whether that's a steal or a trap.
Aliteq Team · Aug 8 · 8 min
12GB is the entry floor for local AI — enough to run genuinely useful models, but with a real ceiling. Here's exactly what 12GB gets you, and when you'll want more.
Aliteq Team · Aug 5 · 10 min
The cheap used pick versus the newer 16GB card. More VRAM and speed, or the lowest price? Here's the honest budget-GPU showdown for local AI.
Aliteq Team · Aug 5 · 10 min
Years on, the RTX 3060 12GB is still the cheapest sensible entry to local AI — 12GB of VRAM for around $200-250 used. Here's honestly how good it still is, and the one price catch.
Aliteq Team · Aug 5 · 10 min
You keep seeing 'R1 distill 8B/14B/32B' — but what does 'distilled' mean, and why is a small distill so good at reasoning? Here's the plain-English explanation.
Aliteq Team · Aug 5 · 10 min