Several Upcoming NVIDIA GeForce & AMD Radeon Laptop GPUs Benchmarked In Geekbench 5: RTX 4070, RTX 4060, RTX 4050, RX 7700S
Earlier this week, both AMD & NVIDIA presented their latest laptop discrete GPU lineup featuring the RDNA 3 & Ada Lovelace architectures. The first laptops based on these GPUs are expected to ship in February next month but it looks like benchmarks for a few of these GPUs have leaked out ahead of their launch. But before we get into the performance, let’s take a quick look at the specs these GPUs have on offer. NVIDIA GeForce RTX 4070 & RTX 4060 Laptop GPUs - 8 GB Targeting The Mainstream The NVIDIA GeForce RTX 4070 and RTX 4060 will feature 8 GB GDDR6 memory. Both GPUs will get a standard 35W profile and up to 115W TGP along with the 25W Dynamic Boost Range. The NVIDIA GeForce RTX 4070 will come with 4608 Cores, 8 GB memory, up to 2175 MHz boost clocks, and a 128-bit bus while the RTX 4060 will feature 3072 Cores, 8 GB memory, up to 2370 MHz boost clocks, and a 128-bit bus. NVIDIA GeForce RTX 4050 6 GB Laptop GPU - Entry-Level Ada For Mobility Lastly, we have the entry-level GeForce RTX 4050 6 GB which will also get a 35W-115W TGP option (25W Dynamic Boost profile too). The GPU will get a boost clock of up to 2370 MHz at its 115W TGP range. The GPU can clock down to 1605 MHz and will feature a 96-bit bus interface. AMD Radeon RX 7700S 8 GB Laptop GPU - Navi 33 For Mainstream Gamers The AMD Radeon RX 7700S is based on the RDNA 3 architecture and utilizes the Navi 33 GPU. It features 32 Compute Units with 2048 shader processors, 8 GB of GDDR6 memory at 18 Gbps, and a 128-bit bus interface. The GPU is stacked with 32 MB of Infinity cache and the TDP is rated at 75-100W. Now coming to the performance benchmarks, we have performance leaks within multiple laptops so it’s hard to say what TGP limits were used by each design. Since all GPUs have a variable range, it’s not wise to compare them together unless or until we actually know their power figures. These GPUs are also heavily dependent on the cooling capabilities of each laptop so that must also be a point of consideration. You can’t say the RTX 4060 or an RTX 4070 is better than the RX 7700S if it’s running at its base-line 75W TDP versus 115W TGPs of the NVIDIA GPUs which is their peak limit. Following are what laptops and what max clock speeds each GPU was tested at:
RTX 4070: Thunderbolt ZERO Laptop (2175 MHz Peak Clock) / 35-115W RTX 4060: Thunderbolt ZERO Laptop (2370 MHz Peak Clock) / 35-115W RTX 4050: Notebook NP5x Laptop (2280 MHz Peak Clock) / 35-115W RX 7700S: ASUS TUF A16 Laptop (2208 MHz Peak Clock) / 75-100W
Anyways, the following are how the AMD Radeon RX 7000 and NVIDIA GeForce RTX 40 Laptop GPUs stack up within the Geekbench 5 OpenCL benchmark: As you can see, the AMD Radeon RX 7700S comes out to be the slowest GPU, even trailing behind the GeForce RTX 4050. Now OpenCL isn’t the best performance indicator for Radeon GPUs but the NVIDIA GPUs, (RTX 4070, RTX 4060, RTX 4050) sit 40%, 25% & 4% faster, respectively versus the new Navi 33 GPU. The AMD Radeon RX 7600M XT is the fastest GPU that AMD plans to offer next month and that doesn’t even come close to NVIDIA’s high-end options such as the RTX 4090 and RT 4080 for laptops. It will definitely be interesting to see the performance of the next-gen mobility GPUs on a per-laptop basis. Currently, there are several NVIDIA RTX 40 & RX 7000M/S designs unveiled by a range of manufacturers but we will see if AMD can actually manage to get all-AMD laptops out on time this year compared to their previous Radeon 5000 and Radeon 6000 series offerings. News Source: Benchleaks
