GPU Comparison

A

AMD

RADEON

ATI FireMV 2250 PCIe x1

CORE STATE RV516

VRAM 256 MB

CLOCK SPEED —

TDP 32 W

BUS WIDTH 128 bit

ARCHITECTURE Ultra-Threaded SE

nm

PROCESS 90 nm

LAUNCH DATE —

VS

NVIDIA

GEFORCE

GeForce RTX 5070

CORE STATE GB205

VRAM 12 GB

CLOCK SPEED 2512 MHz

TDP 250 W

BUS WIDTH 192 bit

ARCHITECTURE Blackwell 2.0

nm

PROCESS 5 nm

LAUNCH DATE 2025

PERFORMANCE BENCHMARKS

3dmark_3dmark_steel_nomad_dx12

N/A

5,077

geekbench_opencl

N/A

185,269

geekbench_vulkan

N/A

179,413

passmark_directx_10

N/A

180

passmark_directx_11

N/A

277

passmark_directx_12

N/A

108

passmark_directx_9

N/A

320

passmark_g2d

N/A

1,305

passmark_g3d

N/A

29,137

passmark_gpu_compute

N/A

15,787

DETAILED SPECIFICATIONS

SPECIFICATION

ATI FireMV 2250 PCIe x1

RTX 5070

Core Specs

Shading Units

—

6,144

Shaders

—

6,144

TMUs

4

192 +4700.0%

ROPs

4

80 +1900.0%

SM Count

—

48

Clocks

Base Clock

—

2325 MHz

Boost Clock

—

2512 MHz

GPU Clock

600 MHz

—

Memory Clock

400 MHz 800 Mbps effective

1750 MHz 28 Gbps effective

Memory

Memory Size

256 MB

12 GB

VRAM (MB)

256

12,288 +4700.0%

Memory Type

DDR2

GDDR7

Memory Bus

128 bit

192 bit

Bandwidth

12.80 GB/s

672.0 GB/s

Cache

L1 Cache

—

128 KB (per SM)

L2 Cache

—

48 MB

Performance

Pixel Rate

2.400 GPixel/s

201.0 GPixel/s

Texture Rate

2.400 GTexel/s

482.3 GTexel/s

FP32 (TFLOPS)

—

30.87 TFLOPS

FP64 (TFLOPS)

—

482.3 GFLOPS (1:64)

FP16 (TFLOPS)

—

30.87 TFLOPS (1:1)

AI/RT

RT Cores

—

48

Tensor Cores

—

192

Power

TDP

32 W

250 W

TDP (W)

32

250 +681.3%

Suggested PSU

200 W

600 W

Power Connectors

None

1x 16-pin

Architecture

Architecture

Ultra-Threaded SE

Blackwell 2.0

GPU Name

RV516

GB205

Generation

FireMV Multi-View (2000)

GeForce 50

Process Size

90 nm

5 nm

Transistors

105 million

31,100 million

Die Size

100 mm²

263 mm²

Foundry

UMC

TSMC

Density

1.1M / mm²

118.3M / mm²

API Support

DirectX

9.0c (9_3)

12 Ultimate (12_2)

OpenGL

2.1

4.6

Vulkan

—

1.4

OpenCL

—

3.0

CUDA

—

12.0

Shader Model

3.0

6.8

Physical

Slot Width

Single-slot

Dual-slot

Length

170 mm 6.7 inches

245 mm 9.6 inches

Height

69 mm 2.7 inches

115 mm 4.5 inches

Outputs

1x S-Video1x DMS-59

1x HDMI 2.1b3x DisplayPort 2.1b

Bus Interface

PCIe 1.0 x1

PCIe 5.0 x16

Other

Launch Price

—

549 USD

Production

End-of-life

Active

Predecessor

—

GeForce 40

View ATI FireMV 2250 PCIe x1 Details View GeForce RTX 5070 Details