The first details of the GPU featured on the N1X SoC have started to emerge from Geekbench, which offers the same core count as RTX 5070.
NVIDIA N1X SOC Packs A "Blackwell" GPU With The Same Core Count As The RTX 5070, Much Work To Be Done On The Performance Side
A few hours ago, the first entry of NVIDIA's N1X showed up in Geekbench's OpenCL browser. While we have already reported the CPU aspects of the SOC, the GPU side information was still a bit lacking. But now we know what the chip has to offer.
The N1X entry shows that the SOC will be packing a Blackwell GPU with the same core count as the RTX 5070. This means we will be seeing 6144 core arranged within 48 SM units. The RTX 5070 uses the GB205 GPU, but it is unclear if the N1X is using a similar silicon or a custom variant. The RTX 5070 packs a total of 192 TMUs, 80 ROPs, 48 RT Cores, and 192 Tensor Cores. It also comes with dedicated 12 GB of GDDR7 memory with up to 672 GB/s bandwidth. Clock speeds for the dedicated graphics card boost up to 2512 MHz on a 250W TDP.
The Geekbench listing shows that the N1X's GPU was barely pushing it beyond 1.05 GHz, which is vastly lower than the RTX 5070. Furthermore, the chip doesn't have dedicated memory, but instead features the LPDDR5X standard, which is shared between the entire SOC. And lastly, the chip is expected to feature a maximum TDP range of up to 120W, so even if the GPU does get 100W power in graphics-intensive or AI scenarios, it is still 150W behind the dedicated part.
Geekbench OpenCL
Looking at the performance figures, the N1X scored 46,361 points, which puts it above and beyond the other modern day iGPUs but way behind the RTX 5070. Once again, this is due to the fact that not only is this chip severely constrained in the power department, but it is still an early engineering sample. NVIDIA will be tweaking the performance for its N1X SOCs massively before launch.
Also, the N1X, given its 120W or so TDP, should be compared against the Strix Halo "AMD Ryzen AI Max" offerings, which feature a similarly large GPU. Those provide much better performance, but once again, it remains to be seen just how much performance NVIDIA can extract out of these chips before launch.
Current rumors allege that the N1X SOC will be launching sometime in 2026, with some claiming the first half and others claiming the latter half of the year. With that said, N1X will make the SOC segment a lot more competitive than it is, and will be NVIDIA's first-ever chance to really compete against x86 and Arm giants such as Intel, AMD, Qualcomm, and Apple.
NVIDIA N1X SOC Specs (Preliminary):
| Name | NVIDIA N1X |
|---|---|
| Process Tech | TSMC N3 |
| Architecture | Grace + Blackwell |
| CPU Cores | 20 (10 Cortex-X925+10 Cortex-A725) |
| GPU Cores | 6144 Cores (48 SMs) |
| Memory | LPDDR5X (Up To 128 GB) |
| Memory Speed | 8533 MT/s |
| TDP | 100-120W (Peak) |
| Launch | 2026 |
About the author: A Software Engineer by training and a PC enthusiast by passion, Hassan Mujtaba serves as Wccftech's Senior Editor for hardware section. With years of experience in the industry, he specializes in deep-dive technical analysis of next-generation CPU and GPU architectures, motherboards, and cooling solutions. His work involves not only breaking news on upcoming technologies but also extensive hands-on reviews and benchmarking.
Follow Wccftech on Google to get more of our news coverage in your feeds.
