22 articles · newest first
$1,679.99 from Amazon today, against a $999 launch price and a $1,249.99 tracked low. The price record, what the extra $500 over a 5070 Ti buys on Nvidia's own spec sheet, and the numbers to buy at.
Voltage · Sep 25 · 7 min
The RTX 5050 is the cheap pick and the RX 9070 is the overall pick. Only one of them still makes sense a year from now.
Voltage · Aug 24 · 7 min
Every major GPU tracker just posted its worst numbers of the year. I went through the wreckage to find what's still a fair price.
Ledger · Aug 15 · 6 min
12GB of VRAM for around $300 sounds like the easy answer to Nvidia's price spike. It mostly is — you just have to fight the drivers a little.
Voltage · Aug 15 · 6 min
Nvidia's mid-range GPU is up 36% in two months — here's whether it still makes sense for running models at home, or if $900 changes the answer entirely.
Voltage · Aug 15 · 6 min
Owners with decade-old GTX cards still running fine say the real lifespan number isn't what upgrade-cycle marketing wants you to believe.
Voltage · Aug 7 · 6 min
The Ryzen 7 9800X3D is the CPU every gaming build guide wants you to buy right now. If you're building for local AI too, here's where that money should actually go instead.
Voltage · Aug 4 · 7 min
South Korea is the canary. TSMC wafer costs and $20 memory chips just pushed the RTX 5090 to 2.5x its sticker price — here's the actual buy-or-skip math for running AI models at home.
Voltage · Aug 4 · 8 min
It launched at $249 promising a fresh budget option. A few months later, a used RTX 3070 for about the same money makes it a hard sell.
Voltage · Aug 3 · 6 min
Instinct MI400 and Helios racks got the headlines at Advancing AI 2026 — but the actual local-AI hardware for individuals already exists, and it's cheaper than an RTX 5090.
Tensor · Aug 1 · 7 min
It's slow, it's old, and it has more VRAM than cards costing twice as much. For a first local-AI GPU, the humble 3060 12GB is still the smart-money entry point.
Voltage · Jul 28 · 9 min
On paper, 12GB for $249 is the best VRAM-per-dollar in new cards. In practice, Intel's software stack is the catch. Here's the honest verdict for local AI.
Tensor · Jul 28 · 9 min
It's the value middle of the Blackwell lineup: 16GB of fast GDDR7, NVFP4 support, and enough speed to run the 14B tier comfortably without paying 5090 money. Is it the right local-AI card for you?
Voltage · Jul 28 · 9 min
Qwen3-32B at Q4 needs about 20GB of VRAM, which rules out every 16GB card and makes this a simple question: what's the cheapest 24GB GPU that runs it well? The answer is used.
Voltage · Jul 28 · 9 min
Llama 70B needs about 40GB of VRAM to run well — and almost no single consumer card has it. Here's what actually works, visualized, with the measured speeds and real costs for each path.
Voltage · Jul 23 · 10 min
Every 'best budget GPU' list is a spec dump. This is a decision: three cards under $500, what each can actually run, and the one number — VRAM — that tells you which to buy without reading a benchmark.
Voltage · Jul 22 · 9 min
Blackwell versus the old flagship, and for once the newer card loses. The 5080's 16GB caps what you can run; the 4090's 24GB doesn't. For local models, capacity beats the spec sheet — with the measured numbers to prove it.
Voltage · Jul 22 · 9 min
The RX 7900 XTX gives you 24GB cheaper than a 3090. The catch isn't what you've heard — a llama.cpp scoreboard and an open bug report suggest its Vulkan backend beats ROCm for inference, no painful install required.
Tensor · Jul 22 · 9 min
A new RTX 5060 Ti 16GB looks like the safe budget pick. But 16GB can't load the 32B models a used 3090 runs at 30 tokens/sec — and in local AI, the card that opens the file wins before speed matters.
Voltage · Jul 22 · 9 min
Measured at 102.7 tokens/sec — double a 3090 — with the only 32GB of VRAM in consumer land. Then the street price doubles the MSRP and the whole verdict flips. Both answers, with the math.
Tensor · Jul 22 · 9 min
Measured llama.cpp numbers say the 4090 wins every speed test and costs twice as much — while energy per generated token is a dead heat. Here's who each card is actually for.
Voltage · Jul 22 · 9 min
the cards are done. they're sitting at board partners right now. what's stopping them from shipping? a single memory chip that costs about $50 more than the one it replaces.
Voltage · Jul 18 · 4 min