GeekRadar / The comparison desk

COMPARE.

GPU

NVIDIA

NVIDIA RTX 2000 Max-Q Ada Generation

Graphics processor

Video memory: 8 GB^*
Memory bus: 128 bit^*
Rated memory bandwidth: 256 GB/s^*

No matched benchmark results are available for this entry yet.

Processing & platform

Architecture: Ada Lovelace^*
Process node: 5 nm^*
GPU cores: 3,072^*
Graphics interface: PCIe 4.0 x16^*
Reported chip die area: 159 mm²^*
Transistors: 18,900 million^*
GPU L2 cache: 12 MB^*
Graphics processor: AD107^*
Texture mapping units: 96^*
Raster output units: 48^*
Streaming multiprocessors: 24^*
Tensor cores: 96^*
Ray tracing cores: 24^*
Chip foundry: TSMC^*
Card or module format: IGP^*
Declared GPU TDP: 35 W^*
External power connectors: None^*
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: 8^*
Video memory: 8 GB^*
Video memory type: GDDR6^*
Memory bus: 128 bit^*
Rated memory bandwidth: 256 GB/s^*

Power specifications

Thermal design power: 35 W^*

System configuration

Detailed specifications

Specifications 1 · 29 fields

proc transistors: 18,900 million^*
proc die size: 159^* mm²
cores: 3,072^*
tensor cores: 96^*
rt cores: 24^*
sm count: 24^*
base clock: 930^*
boost clock: 1,455^*
memory clock: 2,000^*
ram: 8^*
name: NVIDIA RTX 2000 Max-Q Ada Generation^*
ram type: GDDR6^*
bus width: 128^*
bus interface: PCIe 4.0 x16^*
ram bandwidth: 256^* GB/s
fp16 performance: 8.94^*
fp32 performance: 8.94^*
fp64 performance: 0.1397^*
tdp: 35^* W
slot width: IGP^*
api cuda: 8.9^*
is retail board: No^*
gpi value: 5.45^*
vendor: nvd^*
manufacturer: NVIDIA^*
arch name: Ada Lovelace^*
card release date: 2023-03-21^*
proc foundry: TSMC^*
proc process size: 5^* nm

Specifications 2 · 39 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

128^* bit

Reported shader processors

3,072^*

Reported theoretical FP16 peak

8.94^* TFLOPS

Scope and conditions

Arithmetic density: Not stated^*

Reported theoretical FP32 peak

8.94^* TFLOPS

Scope and conditions

Arithmetic density: Not stated^*

Reported theoretical FP64 peak

0.1397^* TFLOPS

Scope and conditions

Arithmetic density: Not stated^*

Declared L1 cache configuration

128 KB (per SM)^*

Declared GPU L2 cache

12 MB^*

Reported display outputs

Portable Device Dependent^*

Theoretical pixel fill rate

69.84 GPixel/s^*

External power connectors

None^*

Reported chip die area

159 mm²^*

Chip foundry

TSMC^*

Process node declaration

5 nm^*

Transistors

18,900 million^*

Graphics processor

AD107^*

Reported video memory

8^* GB

Rated memory bandwidth

256.0 GB/s^*

Video memory type

GDDR6^*

Raster output units

48^*

Ray tracing cores

24^*

Reported shading units

3,072^*

Card or module format

IGP^*

Streaming multiprocessors

24^*

2:4 tensor sparsity

Yes^*

Declared GPU TDP

35 W^*

Tensor cores

96^*

Theoretical texture fill rate

139.7 GTexel/s^*

Texture mapping units

96^*

GPU cores

3,072^*

Video memory

8^* GB

Video memory type

GDDR6^*

* Provisional data