GPU Comparison

NVIDIA

GEFORCE

NVIDIA CMP 90HX

CORE STATE GA102

VRAM 10 GB

CLOCK SPEED 1710 MHz

TDP 320 W

BUS WIDTH 320 bit

ARCHITECTURE Ampere

PROCESS 8 nm

LAUNCH DATE 2021

NVIDIA

GEFORCE

GeForce RTX 4070

CORE STATE AD104

VRAM 12 GB

CLOCK SPEED 2475 MHz

TDP 200 W

BUS WIDTH 192 bit

ARCHITECTURE Ada Lovelace

PROCESS 5 nm

LAUNCH DATE 2023

PERFORMANCE BENCHMARKS

geekbench_opencl

69,000

155,145

3dmark_3dmark_steel_nomad_dx12

N/A

3,854

geekbench_vulkan

N/A

173,261

passmark_directx_10

N/A

139

passmark_directx_11

N/A

244

passmark_directx_12

N/A

103

passmark_directx_9

N/A

320

passmark_g2d

N/A

1,164

passmark_g3d

N/A

26,927

passmark_gpu_compute

N/A

14,720

Analysis: NVIDIA CMP 90HX vs NVIDIA GeForce RTX 4070

Examining the test numbers for the NVIDIA RTX 4070 and NVIDIA's NVIDIA CMP 90HX, a story of competitive frame rates unfolds. Not one GPU wins reliably in all titles. This alternating of wins implies inherent equality. Consumers encounter a real selection with these options. Each options offer capable rendering throughput.

Playing games results also indicate competitive scores between the NVIDIA RTX 4070 and NVIDIA's NVIDIA CMP 90HX. FPS gaps often land under 5-10%. These slight variations are hardly perceptible during actual gaming sessions. The two GPUs achieve capable performance. Gaming enthusiasts should pick assuredly between these two.

At the end of the day, consumers can select based on ecosystem preference over absolute scores exclusively. Each the NVIDIA RTX 4070 and NVIDIA's NVIDIA CMP 90HX provide strong graphics results for their given categories. The determination depends on individual preferences. Both pick is valid. You shouldn't go wrong between them.

DETAILED SPECIFICATIONS

SPECIFICATION

CMP 90HX

RTX 4070

Core Specs

Shading Units

6,400

5,888 -8.0%

Shaders

6,400

5,888 -8.0%

TMUs

200

184 -8.0%

ROPs

64 -20.0%

SM Count

46 -8.0%

Clocks

Base Clock

1500 MHz

1920 MHz

Boost Clock

1710 MHz

2475 MHz

Memory Clock

1188 MHz 19 Gbps effective

1313 MHz 21 Gbps effective

Memory

Memory Size

10 GB

12 GB

VRAM (MB)

10,240

12,288 +20.0%

Memory Type

GDDR6X

Memory Bus

320 bit

192 bit

Bandwidth

760.3 GB/s

504.2 GB/s

Cache

L1 Cache

128 KB (per SM)

L2 Cache

5 MB

36 MB

Performance

Pixel Rate

136.8 GPixel/s

158.4 GPixel/s

Texture Rate

342.0 GTexel/s

455.4 GTexel/s

FP32 (TFLOPS)

21.89 TFLOPS

29.15 TFLOPS

FP64 (TFLOPS)

342.0 GFLOPS (1:64)

455.4 GFLOPS (1:64)

FP16 (TFLOPS)

21.89 TFLOPS (1:1)

29.15 TFLOPS (1:1)

AI/RT

RT Cores

46 -8.0%

Tensor Cores

200

184 -8.0%

Power

TDP

320 W

200 W

TDP (W)

320

200 -37.5%

Suggested PSU

700 W

550 W

Power Connectors

2x 8-pin

1x 16-pin

Architecture

Ampere

Ada Lovelace

GPU Name

GA102

AD104

Generation

Mining GPUs

GeForce 40

Process Size

8 nm

5 nm

Transistors

28,300 million

35,800 million

Die Size

628 mm²

294 mm²

Foundry

Samsung

TSMC

Density

45.1M / mm²

121.8M / mm²

API Support

DirectX

12 Ultimate (12_2)

OpenGL

4.6

Vulkan

1.4

OpenCL

3.0

CUDA

8.6

8.9

Shader Model

6.8

Physical

Slot Width

Dual-slot

Length

285 mm 11.2 inches

240 mm 9.4 inches

Height

112 mm 4.4 inches

110 mm 4.3 inches

Outputs

No outputs

1x HDMI 2.13x DisplayPort 1.4a

Bus Interface

PCIe 1.0 x4

PCIe 4.0 x16

Other

Launch Price

—

599 USD

Production

End-of-life

Predecessor

—

GeForce 30

Successor

—

GeForce 50

View CMP 90HX Details View GeForce RTX 4070 Details