A review here is an assessment of what a piece of hardware can do for a specific kind of work — not a tour of its box contents.
Every review is scored against the same nine criteria, so that a 7 for thermals means the same thing on a mini PC as on a workstation GPU. The rubric, the score bands and what we measure are all published in our review methodology.
What every review tells you
- The score, and its breakdown across all nine criteria — never a single number with no working shown
- Who should buy it, and who should not
- What it can actually run, stated with the quantisation, because “runs 70B” without qualification means nothing
- The trade-offs, in plain terms — power draw, noise, memory that cannot be upgraded
- What to consider instead, including the previous generation where it remains competitive
About our testing
We are a young publication and we have not physically tested most of the hardware we cover. Rather than imply otherwise, every review states its basis directly under the headline: specification analysis, third-party benchmark synthesis, or hands-on testing.
Specification-led analysis is genuinely useful — memory capacity, bandwidth, bus width and power draw are published facts, and a great deal follows from them. What it cannot tell you is how loud a machine gets after an hour at load, or whether the firmware is any good. Where those questions matter, we say that they are open.
Latest reviews
- Review AMD Radeon RX 9070 XT Review: A Better Card That Runs Models Worse Newer, more efficient and architecturally improved — with 50% less memory and 49% less bandwidth than the card it follows. For local…
- Review AMD Radeon RX 7900 XTX Review: The Hardware Is Not the Problem The only new card near this price with 24 GB, and it beats both 16 GB NVIDIA options on the specifications that…
- Review NVIDIA RTX PRO 6000 Blackwell Review: Not Faster, Just Able The same memory bandwidth as an RTX 5090 with three times the capacity — so you are not buying speed. You are…
- Review NVIDIA GeForce RTX 4060 Ti 16GB Review: Superseded, and Worth It Only on Price The slowest card reviewed here, replaced by one with 56% more bandwidth for 15 W more — and the single card on…
- Review NVIDIA GeForce RTX 3090 Review: Still the Answer, and Not Forever Eleven articles on this site lean on this card. Twenty-four gigabytes for the least money is still unbeaten — and the risks…
- Review NVIDIA GeForce RTX 5060 Ti 16GB Review: The Cheapest Way Into 16 GB, and the Slowest Exactly half an RTX 5070 Ti's bandwidth at exactly the same capacity — and the only way to get 16 GB of…
- Review NVIDIA GeForce RTX 5070 Ti Review: Best New, Which Is Not the Same as Best The card this site keeps calling the value pick, tested against that claim — including the used RTX 3090 that beats it…
- Review NVIDIA GeForce RTX 4090 Review: Brilliant at the Work Language Models Do Not Do Twenty-four gigabytes and a 56% shader advantage over a used 3090 — almost none of which language model generation uses. An excellent…
- Review NVIDIA GeForce RTX 5080 Review: Fast, and Standing Next to the Wrong Card Excellent for image generation and held back for language models by 16 GB — with the RTX 5070 Ti offering 93% of…
- Review NVIDIA GeForce RTX 5090 Review: The 32GB Threshold The fastest consumer card for local AI, and the only one that runs 32B-class models properly. It still does not reach 70B…