GeForce RTX 5070

GeForce RTX 5070
  • Graphics Processor: GB205-300
  • Cores: 6144
  • TMUs / ROPs: 192 / 80

Review

Gaming
64
Workstation
61
AI/ML
54
Energy Efficiency
48
NanoReview Final Score
61
Compare GeForce RTX 5070 with other GPUs

Games

FPS Table
Forza Horizon 5
197
140
130
97
The Witcher 3
216
183
131
71
Counter-Strike 2
293
210
160
81
Far Cry 6
164
145
128
82
Hogwarts Legacy
140
117
92
51
CoD: Modern Warfare III
178
171
136
89
Ghost of Tsushima
123
107
89
58
Cyberpunk 2077
164
144
99
43
Shadow of the Tomb Raider
253
238
189
98
Average FPS by Resolution
1080p High 192
1080p Ultra 162
1440p Ultra 128
4K Ultra 74
Margin of Error Low

Test in Benchmarks

Performance tests in graphics benchmarks and applications

3D Mark

Multiplatform graphics benchmark suite that directly correlates with performance in modern games
Steel Nomad Lite Score
23223
Time Spy 22708
Solar Bay 107004
Port Royal 14498
Fire Strike 58324
Wild Life Extreme 43879
Night Raid 172064
Sources: 3DMark [1]

GeekBench 6 OpenCL

GPU test for computational tasks (image processing, photography, computer vision, and ML)
GB6 Compute Score
190967
Background Blur 254.4 img/sec
Face Detection 180.6 img/sec
Horizon Detection 7.91 Gpixels/sec
Edge Detection 10.2 Gpixels/sec
Gaussian Blur 10.7 Gpixels/sec
Feature Matching 1.84 Gpixels/sec
Stereo Matching 975.7 Gpixels/sec
Particle Physics 27816.5 FPS
API OpenCL
Sources: Geekbench [3]

Passmark Graphics

Videocard test that focuses on compute shaders, multi-texturing, tessellation, and other features
G3D Mark Score
28651
G2D Mark 1289
DirectX 11 279 FPS
DirectX 12 106 FPS
GPU Compute 14323 Ops/s
Sources: PassMark [5] – 23210 samples

Blender

Rendering performance test for 3D modeling
Blender GPU
6109.17
Sources: Blender [9] – 1904 samples

Artificial Intelligence Tests

Performance in machine learning and artificial intelligence tasks

GeekBench 6 ML

Tests throughput of AI operations in single, half, and quantized precision
GB6 ML Single Precision
30221
GB6 ML Half Precision
53037
GB6 ML Quantized
23474
Image Classification (SP) 12270
Image Segmentation (HP) 30237
Image Super Resolution (Q) 35585
Face Detection (HP) 62662
Pose Estimation (Q) 145190
Text Classification (SP) 4198
Machine Translation (HP) 6233
Object Detection (SP) 16709
Depth Estimation (Q) 58300
Style Transfer (SP) 246598
Framework ONNX
Backend DirectML
Sources: Geekbench [9]

Specifications

Detailed technical specifications of the GeForce RTX 5070

General

Vendor Nvidia
Build Discrete
Released January 7, 2025
Launch price (MSRP) $549
Case Desktop
Purpose Gaming
Segment Mid-range
Architecture Blackwell 2.0
GPU Codename GB205-300
AMD Equivalent - Radeon RX 9070
Recommended CPU - Intel Core Ultra 5 245K or above
Desktop GPU rating - 21st place

Graphics Processing Unit

Base Clock 2160 MHz
Boost Clock 2512 MHz
Shading Units 6144
Texture Mapping Units (TMUs) 192
Render Output Units (ROPs) 80
Compute Units (Pipelines) 48
Tensor Cores 192
Ray-tracing Cores 48
L1 Cache 128KB per cluster
L2 Cache 48MB shared
Instructions Per Cycle 2 IPC

Raw Performance

Pixel Fill Rate 201 GPixel/s
Texture Fill Rate 482 GTexel/s
FLOPS (FP32)
30.9 TFLOPS

Physical

Interface PCIe 5.0 x16
TGP 250 W
Manufacturing TSMC
Fabrication Process 4 nm
Die Size 263 mm²
Transistor Count 31.1 billion
Transistor Density 118.25 MTr/mm²

Memory

Memory Type GDDR7
Memory Size 12 GB
Memory Clock 1750 MHz
Effective Memory Speed 28000 Mbps
Bus 192-bit
ECC No
Memory Bandwidth
672 GB/s

API

DirectX 12.2
Vulkan 1.4
OpenGL 4.6
OpenCL 3.0
CUDA 12.0
Ray Tracing Yes
DLSS DLSS 4
DisplayPort 2.1b

Comments

Do you have any questions about RTX 5070? Please, use comment form below
🌐 Register your profile and become part of NanoReview community!