NVIDIA GeForce RTX 4070 Ti

The Nvidia GeForce RTX 4070 Ti is a high-end desktop graphics card based on the AD104 chip using the Ada Lovelace architecture. The 4070Ti offers 7,680 cores and 12 GB GDDR6X graphics memory with a 192 bit memory bus and clocked at 22.4 Gbits. The card offers a good raytracing performance thanks to the 60 dedicated raytracing cores. For AI calculations (and DLSS 3 in games), the RTX 4070 Ti has 240 Tensor cores.

The gaming performance is well suited for 4k60 gaming in most games, but for very demanding games you might have to reduce to QHD resolution. With Raytracing, lower resolutions and DLSS are crucial for playable frame rates. The performance on average is similar to the old RTX 3090 / 3090 Ti.

The AD104 chip is manufactured in the modern 4nm process at TSMC (4N with EUV) and specified with a TGP (Total Graphics Power) of 285 Watt (compared to the 450 Watt of the RTX 4090).

GeForce RTX 4000 Series NVIDIA GeForce RTX 4090 16384 @ 2.24 - 2.52 GHz 384 Bit @ 21000 MHz NVIDIA GeForce RTX 4080 9728 @ 2.21 - 2.51 GHz 256 Bit @ 22400 MHz NVIDIA GeForce RTX 4070 Ti 7680 @ 2.31 - 2.61 GHz 192 Bit @ 21000 MHz
Codename	AD104-400
Architecture	Ada Lovelace
Pipelines	7680 - unified
TMUs	240
ROPs	80
Raytracing Cores	60
Tensor / AI Cores	240
Core Speed	2310 - 2610 (Boost) MHz
Theoretical Performance	40.1 TFLOPS FP16, 40.1 TFLOPS FP32, 0.63 TFLOPS FP64
Cache	L2: 48 MB
Memory Speed	21000 effective = 1313 MHz
Memory Bus Width	192 Bit
Memory Type	GDDR6X
Max. Amount of Memory	12 GB
Shared Memory	no
Memory Bandwidth	504.2 GB/s
API	DirectX 12 Ultimate, Shader 12_2, OpenGL 4.6, OpenCL 3.0, Vulkan 1.3
Power Consumption	285 Watt
Transistor Count	35.8 Billion
Die Size	295 mm²
technology	4 nm
PCIe	4.0 x16
Displays	4 Displays (max.), HDMI 2.1, DisplayPort 1.4a
Date of Announcement	03.01.2023
Predecessor	GeForce RTX 3070 Ti

Benchmarks