GPU

NVIDIA GeForce RTX 4070 Ti SUPER

Memory

16GB GDDR6X, 256bit, 21Gbps, 1313MHz, 672GB/​s

clock Base

2340MHz

clock Boost

2640MHz

overclock

+30MHz Boost

Cooling

3x Axial-fan (100mm) with 0dB-zero-fan-mode

TDP/TGP

285W (NVIDIA), max. 295W (Palit)

Power connections

1x 16-Pin PCIe 5.0 (via adapter: 2x 8-Pin PCIe)

Connectors

1x HDMI 2.1a, 3x DisplayPort 1.4a

Interface

PCIe 4.0 x16

Special features

Backplate, Graphics Cards-Mounting

total height

Quad Slot (3.5 Slots)

Dimensions

329.4x137.5x71.5mm (LxWxH)

Type

PCIe card (full height)

Computing power

44.61 TFLOPS (FP16), 44.61 TFLOPS (FP32), 0.7 TFLOPS (FP64)

Chip-data

Chip-Architecture

Ada Lovelace (from 2022/​Q3)

Chip-title

AD103-275-A1

Chip-Configuration

66SM (8448SP /​ 264TMU /​ 96ROP), 66 RT Cores, 264 Tensor Cores, 48MB L2 cache

Chip-Manufacturing Process

TSMC 5nm "NVIDIA 4N"

Chip size

379mm², monolithisch, 45.9 Mrd. Transistoren

Chip-functions

Raytracing (3rd Gen NVIDIA RTX), NVIDIA Tensor (4th Gen), HDCP 2.3

API-support

DirectX 12 Ultimate (12_2) /​ CUDA 8.9 /​ Vulkan 1.3 /​ OpenCL 3.0 /​ OpenGL 4.6 /​ Shader Model 6.7

Transcoding-Engine

2x NVENC (8th Gen, max. Sessions: 8), 1x NVDEC (5th Gen), Info

encoding

AV1, H.265 (4K YUV 4:2:0 /​ 4K YUV 4:4:4 /​ 4K Lossless /​ 8K /​ HEVC 10bit support /​ HEVC B Frame support), H.264 (YUV 4:2:0 /​ YUV 4:4:4 /​ Lossless)

decoding

AV1 (8bit /​ 10bit), H.265 (8bit 4:2:0 /​ 10bit 4:2:0 /​ 12bit 4:2:0 /​ 8bit 4:4:4 /​ 10bit 4:4:4 /​ 12bit 4:4:4), H.264, VP9 (8bit /​ 10bit /​ 12bit), VP8, VC-1, MPEG-2, MPEG-1