Nvidia’s GeForce RTX 4070 is here. This is the company’s first launch in more than a year of a graphics card that can be condescendingly called “mainstream”in terms of both performance and price. It costs 600 dollars.
It’s unproductive to keep going back to the $600 GTX 1080, at the time the fastest graphics card you could buy anywhere and from anyone, and wonder how we got here from there (partly it’s inflation, not all ). But I keep doing this as a reminder that $600 is still more than what many people pay for their entire PC, tablet, smartphone, or high-end gaming console. No other gaming PC component has seen such a price spike in the same time period; a Core i5 processor cost about $200 in 2016 and is now around $200, and RAM and SSDs are historically cheap at the moment.
Looking at the 4070 is both being impressed by it as a product and being frustrated at the same time by the conditions that led us to the “impressive”$600 mid-range graphics card. It’s pretty fast, very efficient, and much more reasonably sized than other recent Nvidia GPUs. In today’s upside-down graphics card market, I’d even call it a good deal. But if you’re still longing for the days when you could spend $300 or less on a reasonably capable GPU with the latest architecture and modern features, keep waiting.
RTX 4070 and 40 series update
The Founders Edition RTX 4070 we reviewed is significantly smaller in every way than the Founders Edition RTX 4080 and RTX 4090, as well as most 4070/4070 Ti/4080/4090 cards from Nvidia partners. The dual-slot GPU is just 240mm long (up from 310mm on the 4080/4090) and 40mm high (up from 61mm). That’s not counting the extra space taken up by the 12VHPWR-8-pin power connector, which is still quite bulky even though it only requires a pair of 8-pin connectors rather than three or four. But it’s still a card small enough to fit in just about any PC case, including pre-built OEM mini-towers and tiny custom ITX builds.
The RTX 4070 has a lot in common with the 4070 Ti, a GPU originally billed as “RTX 4080 12GB”before it was “shut down”and restarted. They use the same AD104 GPU die, a smaller chip than the flagship AD102 used in the RTX 4090 or the AD103 used in the 4080 series. They also use 12GB of GDDR6X memory on a 192-bit interface. The 4070 has fewer CUDA cores (5888 compared to the 7680), but the 4070 and 4070 Ti are much more similar than the 16GB and 12GB RTX 4080 cards.
This 192-bit memory interface is narrower than the 256-bit interface used by the 3070 and 3070 Ti, which Nvidia made up for by adding 32MB of additional L2 cache to the 4070 (36MB in total). This cache and much higher base and boost clock speeds are the 4070’s biggest improvements over the last generation cards.
| RTX 4090 | RTX 4080 | RTX 4070 Ti | RTX 4070 | RTX 3080 Ti | RTX 3080 10 GB | RTX 3070 Ti | RTX 3070 | RTX 3060 | |
|---|---|---|---|---|---|---|---|---|---|
| CUDA cores | 16 384 | 9728 | 7680 | 5888 | 10 240 | 8704 | 6144 | 5888 | 3584 |
| Clock boost | 2520 MHz | 2505 MHz | 2610 MHz | 2475 MHz | 1665 MHz | 1710 MHz | 1765 MHz | 1725 MHz | 1777 MHz |
| Memory bus width | 384-bit | 256-bit | 192 bit | 192 bit | 384-bit | 320 bit | 256-bit | 256-bit | 192 bit |
| Memory Clock | 1313 MHz | 1400 MHz | 1313 MHz | 1313 MHz | 1188 MHz | 1188 MHz | 1188 MHz | 1750 MHz | 1875 MHz |
| Memory | 24GB GDDR6X | 16GB GDDR6X | 12GB GDDR6X | 12GB GDDR6X | 12GB GDDR6X | 10GB GDDR6X | 8GB GDDR6X | 8GB GDDR6 | 12GB GDDR6 |
| THP | 450 W | 320 W | 285 W | 200 W | 350 W | 320 W | 290 W | 220 W | 170 W |
Because it uses the same Ada Lovelace architecture as other RTX 4000 GPUs, the RTX 4070 also supports Nvidia’s new DLSS 3 and related DLSS Frame Generation (DLSS FG) features. DLSS is AI-assisted scaling that takes a lower resolution image generated by your GPU and upscales it, improving high resolution frame rates with relatively little loss of detail.