NVIDIA GeForce RTX 4080

The Nvidia GeForce RTX 4080 is a high-end desktop graphics card based on the AD103 chip using the Ada Lovelace architecture. The 4080 offers 9,728 cores and 16 GB GDDR6X graphics memory with a 256-bit memory bus and clocked at 22.4 Gbits. The card offers a very good ray tracing performance thanks to the 76 dedicated ray tracing cores. For AI calculations (and DLSS 3 in games), the RTX 4080 has 304 Tensor cores.

Performance

The gaming performance is well-suited for 4k60 gaming in maximum detail settings and 2K gaming with higher frame rates. Even ray tracing effects can be used with DLSS in most games. Compared to the competition, the RTX 4080 is on par with the AMD Radeon RX 7900 XT, with a noticeable advantage when raytracing is used.

Power consumption

The AD103 chip is manufactured in the modern 5nm process at TSMC (4N with EUV) and specified with a TGP (Total Graphics Power) of 320 Watts (compared to the 450 Watts of the RTX 4090). Nvidia is recommending a 750-watt power supply for the RTX 4080.

GeForce RTX 4000 Series GeForce RTX 4090 16384 @ 2.24 - 2.52 GHz 384 Bit @ 21000 MHz GeForce RTX 4080 Super 10240 @ 2.3 - 2.55 GHz 256 Bit @ 23000 MHz GeForce RTX 4080 9728 @ 2.21 - 2.51 GHz 256 Bit @ 22400 MHz GeForce RTX 4070 Ti SUPER 8448 @ 2.34 - 2.61 GHz 256 Bit @ 21000 MHz GeForce RTX 4070 Ti 7680 @ 2.31 - 2.61 GHz 192 Bit @ 21000 MHz GeForce RTX 4070 SUPER 7168 @ 1.98 - 2.48 GHz 192 Bit @ 21000 MHz GeForce RTX 4070 5888 @ 1.92 - 2.48 GHz 192 Bit @ 21000 MHz GeForce RTX 4060 Ti 16G 4352 @ 2.31 - 2.54 GHz 128 Bit @ 18000 MHz GeForce RTX 4060 Ti 8G 4352 @ 2.31 - 2.54 GHz 128 Bit @ 18000 MHz GeForce RTX 4060 3072 @ 1.83 - 2.46 GHz 128 Bit @ 17000 MHz
Codename	AD103-300-A1
Architecture	Ada Lovelace
Pipelines	9728 - unified
TMUs	304
ROPs	112
Raytracing Cores	76
Tensor / AI Cores	304
Core Speed	2205 - 2505 (Boost) MHz
Theoretical Performance	48.7 TFLOPS FP16, 48.7 TFLOPS FP32, 0.76 TFLOPS FP64
AI GPU	780 TOPS INT8
Cache	L2: 64 MB
Memory Speed	22400 effective = 1400 MHz
Memory Bus Width	256 Bit
Memory Type	GDDR6X
Max. Amount of Memory	16 GB
Shared Memory	no
Memory Bandwidth	716.8 GB/s
API	DirectX 12 Ultimate, Shader 6.7, OpenGL 4.6, OpenCL 3.0, Vulkan 1.3
Power Consumption	320 Watt
Transistor Count	45.900 Million
Die Size	379 mm²
Man. Technology	5 nm
PCIe	4.0 x16
Displays	4 Displays (max.), HDMI 2.1, DisplayPort 1.4a
Date of Announcement	20.09.2022
Link to Manufacturer Page	www.nvidia.com
Predecessor	GeForce RTX 3080 12 GB

Benchmarks