NVIDIA has introduced three new GPUs for the laptop segment based on its Turing & Ampere architecture, the GeForce RTX 2050, GeForce MX570 & MX550.
NVIDIA Intros GeForce RTX 2050, GeForce MX570 & GeForce MX550 For Entry-Level Gaming Laptops
The NVIDIA GeForce RTX 2050 GPU is the latest laptop gaming SKU based on the Ampere graphics architecture along with the GeForce MX570 while the GeForce MX550 is based on the Turing architecture. It looks like Turing has officially made a comeback on both desktops and laptops in 2021 and there is a good reason given the heated competition from AMD and Intel that's coming next quarter. The NVIDIA RTX 2050 is also a brand new SKU as we haven't seen it on either the desktop or laptop segment before.
Starting with the specifications, the GeForce RTX 2050 is based on the GA107 GPU core with 2048 cores which is actually more than the GeForce RTX 2060 laptop variant. It features a boost clock of up to 1477 MHz and has a TGP of up to 45W. The GPU features 4 GB of GDDR6 memory clocked at 14 Gbps but runs across a 64-bit bus interface which provides 112 GB/s bandwidth. The memory sub-system is the major blow to the RTX 2050 but it makes sense since this is not a replacement of the RTX 2060 but a more entry-level option.
NVIDIA GeForce RTX 20 Series Mobility Lineup (Official Specs):
| Graphics Card Name | NVIDIA GeForce RTX 2050 | NVIDIA GeForce RTX 2060 | NVIDIA GeForce RTX 2070 | NVIDIA GeForce RTX 2080 |
|---|---|---|---|---|
| GPU Core | GA107 | TU106 | TU106 | TU104 |
| Process Node | 8nm | 12nm FFN | 12nm FFN | 12nm FFN |
| CUDA Cores | 2048 CUDA Cores | 1920 CUDA Cores | 2304 CUDA Cores | 2944 CUDA Cores |
| Base Clock | TBA | 960 MHz | 1215 MHz (Laptop) 885 MHz (Max-Q) | 1380 MHz (Laptop) 735 MHz (Max-Q) |
| Boost Clock | 1477 MHz (Laptop) 1155 MHz (Max-Q) | 1560 MHz (Laptop) 1185 MHz (Max-Q) | 1440 MHz (Laptop) 1185 MHz (Max-Q) | 1095 MHz (Laptop) 1590 MHz (Max-Q) |
| RTX-Ops | TBD | 26T | 31-38T | 37-53T |
| Gigarays/s | TBD | 3.5 | 4-5 | 5-7 |
| VRAM | 4 GB GDDR6 | 6 GB GDDR6 | 8 GB GDDR6 | 8 GB GDDR6 |
| Memory Bus | 64-bit | 192-bit | 256-bit | 256-bit |
| Memory Clock | 14 Gbps (Laptop) | 14 Gbps (Laptop) | 14 Gbps (Laptop) 14 Gbps (Max-Q) | 14 Gbps (Laptop) 14 Gbps (Max-Q) |
| Memory Bandwidth | 112 GB/s | 336 GB/s | 448 GB/s | 448 GB/s |
| TDP | 30-45W | 80-90W | 80-115W | 80-150W+ |
Moving over to the GeForce MX570 and MX550, NVIDIA isn't providing detailed specifications but it looks like the MX570 is based on a totally new Ampere GPU SKU, the GA107 while the MX550 uses the Turing TU117 GPU. The GA107 die is already shipping in RTX 3050 laptop SKUs and since the MX series is always the most entry-level die, this would be the most cut-down configuration of the GA107 GPU core.
The GeForce RTX 2050 and MX500 series laptop GPUs support all the latest features such as ray tracing, NVIDIA DLSS, Reflex, and Broadcast, among others. They also work seamlessly with Optimus & are a perfect solution for providing longer battery times with more horsepower over a standard iGPU.
The NVIDIA GeForce RTX 2050 and the GeForce MX570 / MX550 GPUs are expected to ship in entry-level laptops by Spring 2022.
NVIDIA GeForce MX Series GPU Family Specifications:
| GPU Name | GPU Architecture | CUDA Cores | GPU Clock | Memory Speed | Memory Bus | TDP |
|---|---|---|---|---|---|---|
| GeForce MX570 | Ampere GA107 | 2048 | TBA - 1155 MHz | 12 Gbps GDDR6 | 64-bit | 25W |
| GeForce MX550 | Turing TU117 | 1024 | TBA - 1320 MHz | 12 Gbps GDDR6 | 64-bit | 25W |
| GeForce MX 450 | Turing TU117 | 896 | 540 - 1575 MHz | 10 Gbps GDDR6 | 64-bit | 25W |
| GeForce MX 430 | Turing TU117 | 896 | TBA - TBA MHz | 10 Gbps GDDR6 7 Gbps GDDR5 | 64-bit | 25W |
| GeForce MX 350 | Pascal GP107 | 640 | 1354-1468 MHz | 7 Gbps GDDR5 | 64-bit | 25W |
| GeForce MX 350 | Pascal GP107 | 640 | 746-937 MHz | 7 Gbps GDDR5 | 64-bit | 15W |
| GeForce MX 330 | Pascal GP108 | 384 | 1531-1594 MHz | 6/7 Gbps GDDR5 | 64-bit | 25W |
| GeForce MX 310 | Pascal GP108 | 256 | 1341-1379 MHz | 6/7 Gbps GDDR5 | 64-bit | 25W |
| GeForce MX 250 | Pascal GP108 | 384 | 1518-1582 MHz | 6/7 Gbps GDDR5 | 64-bit | 25W |
| GeForce MX 250 | Pascal GP108 | 384 | 937-1038 MHz | 6 Gbps GDDR5 | 64-bit | 10.5W |
| GeForce MX 230 | Pascal GP108 | 256 | 1518-1531 MHz | 6/7 Gbps GDDR5 | 64-bit | 25W |
| GeForce MX 150 | Pascal GP108 | 384 | 1468-1531 MHz | 6 Gbps GDDR5 | 64-bit | 25W |
| GeForce MX 150 | Pascal GP108 | 384 | 937-1038 MHz | 5 Gbps GDDR5 | 64-bit | 10W |
| GeForce MX 130 | Maxwell GM108 | 384 | 1122-1242 MHz | 6 Gbps GDDR5 | 64-bit | 25W |
| GeForce MX 110 | Maxwell GM108 | 256 | 963-993 MHz | 1.8 Gbps DDR3 | 64-bit | 10W |
