GeekRadar / The comparison desk

COMPARE.

GPU

NVIDIA

GeForce RTX 4070 AD103

Graphics processor

Video memory: 12 GB^*
Memory bus: 192 bit^*
Rated memory bandwidth: 504.20 GB/s^*

No matched benchmark results are available for this entry yet.

Processing & platform

Architecture: Ada Lovelace^*
Process node: 5 nm^*
GPU cores: 5,888^*
GPU base clock: 1,920 MHz^*
Graphics interface: PCIe 4.0 x16^*
Reported chip die area: 379 mm²^*
Transistors: 45,900 million^*
GPU boost clock: 2,475 MHz^*
GPU L2 cache: 36 MB^*
Graphics processor: AD103^*
Texture mapping units: 184^*
Raster output units: 64^*
Streaming multiprocessors: 46^*
Tensor cores: 184^*
Ray tracing cores: 46^*
Chip foundry: TSMC^*
Card or module format: Dual-slot^*
Declared GPU TDP: 200 W^*
Suggested system PSU: 550 W^*
External power connectors: 1x 16-pin^*
DirectX / feature level: 12 Ultimate (12_2)^*
OpenGL: 4.6^*
OpenCL: 3.0^*
Vulkan: 1.4^*
CUDA compute capability: 8.9^*
Shader model: 6.9^*

Memory & storage

Memory options: 12^*
Video memory: 12 GB^*
Video memory type: Reported value 1: GDDR6X^*
Reported value 2: GDDR6^*
Reported value 3: GDDR6X^*
Reported value 4: GDDR6X^*
Reported value 5: GDDR6X^*
Memory bus: 192 bit^*
Rated memory bandwidth: 504.20 GB/s^*

Power specifications

Thermal design power: 200 W^*

System configuration

Detailed specifications

Specifications 1 · 31 fields

proc transistors: 45,900 million^*
proc die size: 379^* mm²
cores: 5,888^*
tensor cores: 184^*
rt cores: 46^*
sm count: 46^*
base clock: 1,920^*
boost clock: 2,475^*
memory clock: 1,313^*
ram: 12^*
name: NVIDIA GeForce RTX 4070 AD103^*
ram type: GDDR6X^*
bus width: 192^*
bus interface: PCIe 4.0 x16^*
ram bandwidth: 504.2^* GB/s
fp16 performance: 29.15^*
fp32 performance: 29.15^*
fp64 performance: 0.4554^*
tdp: 200^* W
suggested psu: 550^* W
slot width: Dual-slot^*
power connectors: 1x 16-pin^*
api cuda: 8.9^*
is retail board: No^*
gpi value: 13.23^*
vendor: nvd^*
manufacturer: NVIDIA^*
arch name: Ada Lovelace^*
card release date: 2024-03-13^*
proc foundry: TSMC^*
proc process size: 5^* nm

Specifications 2 · 40 fields

CUDA compute capability

8.9^*

DirectX / feature level

12 Ultimate (12_2)^*

OpenCL

3.0^*

OpenGL

4.6^*

Shader model

6.9^*

Vulkan

1.4^*

Architecture

Ada Lovelace^*

Graphics interface

PCIe 4.0 x16^*

Memory bus

192^* bit

Reported shader processors

5,888^*

Reported theoretical FP16 peak

29.15^* TFLOPS

Scope and conditions

Arithmetic density: Not stated^*

Reported theoretical FP32 peak

29.15^* TFLOPS

Scope and conditions

Arithmetic density: Not stated^*

Reported theoretical FP64 peak

0.4554^* TFLOPS

Scope and conditions

Arithmetic density: Not stated^*

Declared L1 cache configuration

128 KB (per SM)^*

Declared GPU L2 cache

36 MB^*

Reported display outputs

1x HDMI 2.1, 3x DisplayPort 1.4a^*

Theoretical pixel fill rate

158.4 GPixel/s^*

External power connectors

1x 16-pin^*

Reported chip die area

379 mm²^*

Chip foundry

TSMC^*

Process node declaration

5 nm^*

Transistors

45,900 million^*

Graphics processor

AD103^*

Reported video memory

12^* GB

Rated memory bandwidth

504.2 GB/s^*

Video memory type

GDDR6X^*

Raster output units

64^*

Ray tracing cores

46^*

Reported shading units

5,888^*

Card or module format

Dual-slot^*

Streaming multiprocessors

46^*

Suggested system PSU

550 W^*

2:4 tensor sparsity

Yes^*

Declared GPU TDP

200 W^*

Tensor cores

184^*

Theoretical texture fill rate

455.4 GTexel/s^*

Texture mapping units

184^*

GPU cores

5,888^*

Video memory

12^* GB

Video memory type

GDDR6X^*

Specifications 3 · 63 fields

Brand: NVIDIA^*
Top BUS WIDTH: 192^* bit
Graphics Processor GPU Name: AD103^*
Graphics Processor Architecture: Ada Lovelace^*
Render Config SM Count: 46^*
Graphics Features CUDA: 8.9^*
Render Config Tensor Cores: 184^*
Graphics Processor Process Size: 5^* nm
Graphics Processor Transistors: 45,900 million^*
Graphics Processor Die Size: 379^* mm²
Graphics Card Release Date: Mar 2024^*
Graphics Card Generation: GeForce 40^*
Graphics Card Successor: GeForce 50^*
Graphics Card Production: Active^*
Name: GeForce RTX 4070 AD103^*
Graphics Card Bus Interface: PCIe 4.0 x16^*
Clock Speeds Memory Clock: 1313 MHz 21 Gbps effective^*
Memory Memory Size: 12^* GB
Memory Memory Type: GDDR6X^*
Memory Memory Bus: 192^* bit
Memory Bandwidth: 504.2^* GB/s
Render Config TMUs: 184^*
Top GRAPHICS PROCESSOR: AD103^*
Render Config ROPs: 64^*
Theoretical Performance Pixel Rate: 158.4 GPixel/s
Theoretical Performance Texture Rate: 455.4 GTexel/s
Board Design Slot Width: Dual-slot^*
Board Design TDP: 200^* W
Board Design Suggested PSU: 550^* W
Board Design Outputs: 1x HDMI 2.1 3x DisplayPort 1.4a^*
Board Design Board Number: PG141 SKU 370^*
Graphics Features DirectX: 12 Ultimate (12_2)^*
Graphics Features OpenGL: 4.6^*
Graphics Features OpenCL: 3^*
Graphics Features Vulkan: 1.3^*
source file: nvidia2024.json^*
Graphics Processor Foundry: TSMC^*
Graphics Card Predecessor: GeForce 30^*
Recommended Resolutions: Good:1920x1080 | Good:2560x1440 | Good:3840x2160^*
Graphics Card Launch Price: 599 USD^*
Board Design Length: 240 mm 9.4 inches^*
Graphics Processor GPU Variant: AD103-175-K1-A1^*
Board Design Power Connectors: 1x 16-pin^*
Graphics Processor Density: 121.1M / mm²^*
Board Design Height: 110 mm 4.3 inches^*
Board Design Width: 40 mm 1.6 inches^*
Graphics Card Reviews: 53 in our database^*
Top TMUS: 184^*
Top ROPS: 64^*
Clock Speeds Base Clock: 1,920^* MHz
Clock Speeds Boost Clock: 2,475^* MHz
Graphics Features Shader Model: 6.8^*
Top CORES: 5,888^*
Render Config Shading Units: 5,888^*
Render Config L2 Cache: 36^* MB
Top MEMORY SIZE: 12^* GB
Theoretical Performance FP32 (float): 29.15^* TFLOPS
Theoretical Performance FP64 (double): 455.4 GFLOPS (1:64)
Render Config L1 Cache: 128 KB (per SM)^*
Theoretical Performance FP16 (half): 29.15 TFLOPS (1:1)
Graphics Card Availability: Mar, 2024^*
Top MEMORY TYPE: GDDR6X^*
Render Config RT Cores: 46^*

Specifications 4 · 14 fields

manufacturer: NVIDIA^*
rop: 80^*
igp: No^*
bus: PCIe 4.0 x16^*
memType: GDDR6^*
gpuChip: GA104^*
productName: GeForce RTX 4070 AD103^*
releaseYear: 2,024^*
memSize: 12^*
memBusWidth: 192^*
gpuClock: 780^*
memClock: 1,500^*
unifiedShader: 5,120^*
tmu: 160^*

* Provisional data