AMD Radeon RX 9070 XT vs 7900 XT

We compared two discrete desktop gaming GPUs: the Radeon RX 9070 XT 16 GB with 64 pipelines and 4096 shaders against the 1 year and 1 month older 7900 XT 20 GB that utilizes 5376 shaders. Here you will find complete details about specs, efficiency, performance tests, and more.

Review

General comparison of performance in games, applications, power efficiency, and other metrics
Gaming
Performance in DirectX, OpenCL, and Vulkan games
Workstation
Perf. in 3D modeling, video editing and rendering apps
AI/ML
Capabilities for machine learning and AI-related tasks
Energy Efficiency
Power consumption efficiency in different scenarios
NanoReview Final Score
Overall video card score

Value for money (Beta)

We use average GPU prices from all manufacturers by default. Enter the current price of a specific card for better accuracy.
Currency
16 GB GDDR6
VS
20 GB GDDR6
98.8
(Very good)
Value Index
95.3
(Very good)

Key differences

Key distinctions and advantages of RX 7900 XT over RX 9070 XT
Reasons to consider the Radeon RX 9070 XT
  • Manufactured using a more efficient 4 nm process technology
  • Shows 7% higher average frame rate in modern games at QHD resolution – 152 vs 142 FPS
Reasons to consider the Radeon RX 7900 XT
  • Includes 4 GB more video memory
  • Has 24% higher memory bandwidth: 800 vs 644.6 GB/s
  • Has 31% more shading units (5376 vs 4096)

Gaming Performance

Frame rate comparison across popular AAA titles at different resolutions

Games

FPS Table
Forza Horizon 5
242
169
149
109
235
160
141
107
The Witcher 3
267
237
167
89
249
225
160
87
Counter-Strike 2
325
224
163
82
311
222
157
81
Far Cry 6
198
176
163
104
196
168
151
100
Hogwarts Legacy
162
133
107
58
153
124
98
56
CoD: Modern Warfare III
240
232
174
118
228
214
163
108
Ghost of Tsushima
158
137
116
73
150
126
109
69
Cyberpunk 2077
190
171
119
53
181
156
108
49
Shadow of the Tomb Raider
280
265
207
107
271
258
189
101
Average FPS by Resolution
1080p High 229 219
1080p Ultra 194 184
1440p Ultra 152 142
4K Ultra 88 84
Margin of Error Low Low

Benchmarks

Graphics cards’ performance in recent benchmarking apps

3D Mark

Multiplatform graphics benchmark suite that directly correlates with performance in modern games
Steel Nomad Lite Score
26251
24675
Time Spy 29556 27106
Solar Bay 122220 105357
Port Royal 18363 14360
Fire Strike 66319 67227
Wild Life Extreme 54672 48410
Night Raid 194947 176232
Sources: 3DMark [1], [2]

GeekBench 6 OpenCL

GPU test for computational tasks (image processing, photography, computer vision, and ML)
GB6 Compute Score
182816
RX 7900 XT +11%
203754
Background Blur 427.4 img/sec 419.8 img/sec
Face Detection 251 img/sec 240.5 img/sec
Horizon Detection 6.77 Gpixels/sec 8.72 Gpixels/sec
Edge Detection 9.42 Gpixels/sec 12 Gpixels/sec
Gaussian Blur 9.35 Gpixels/sec 9.88 Gpixels/sec
Feature Matching 1.42 Gpixels/sec 1.71 Gpixels/sec
Stereo Matching 651.4 Gpixels/sec 701.7 Gpixels/sec
Particle Physics 23630 FPS 26631.4 FPS
API OpenCL OpenCL
Sources: Geekbench [3], [4]

Cinebench 2024 GPU

Hardware benchmark using Maxon's Cinema 4D rendering engine
Cinebench 2024 GPU
RX 9070 XT +330%
50113
11648

Passmark Graphics

Videocard test that focuses on compute shaders, multi-texturing, tessellation, and other features
G3D Mark Score
26913
29124
G2D Mark 1310 1247
DirectX 11 295 FPS 341 FPS
DirectX 12 77 FPS 112 FPS
GPU Compute 16100 Ops/s 16878 Ops/s
Sources: PassMark [5], [6] – 17863 & 7237 samples

Blender

Rendering performance test for 3D modeling
Blender GPU
3287.07
3558.92
Sources: Blender [9], [10] – 1724 & 949 samples

Recent User Tests

The latest benchmark tests that have been submitted by users
Radeon RX 9070 XT
DateBenchmarkResult
📘 2026-07-12 (luizmdd)Cinebench 202450113
📘 2026-07-04 -> StevenSGeekbench 6 OpenCL179283
📘 2026-07-04 -> StevenSSteel Nomad Light27505
📘 2025-10-15 (adv)Geekbench 6 OpenCL175418
Radeon RX 7900 XT
DateBenchmarkResult
📘 2026-01-01 (Mr Scare)Cinebench 202411648

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
39190
39099
GB6 ML Half Precision
RX 9070 XT +18%
55727
47298
GB6 ML Quantized
33599
30875
Image Classification (SP) 18001 16951
Image Segmentation (HP) 25174 23234
Image Super Resolution (Q) 45714 41128
Face Detection (HP) 74776 67615
Pose Estimation (Q) 196137 237026
Text Classification (SP) 5163 4961
Machine Translation (HP) 8677 7043
Object Detection (SP) 19602 18737
Depth Estimation (Q) 74879 67746
Style Transfer (SP) 411302 457919
Framework ONNX ONNX
Backend DirectML DirectML
Sources: Geekbench [9], [10]

Specifications

Technical specifications of Radeon RX 9070 XT and 7900 XT

General

Vendor Amd Amd
Build Discrete Discrete
Released January 7, 2025 December 13, 2023
Launch price (MSRP) $599 $899
Case Desktop Desktop
Purpose Gaming Gaming
Segment High-end High-end
Architecture RDNA 4.0 RDNA 3.0
GPU Codename Navi 48 Navi 31
Rival Equivalent - GeForce RTX 5070 Ti - GeForce RTX 4080
Recommended CPU - Intel Core Ultra 5 245K or above - Intel Core i7 13700K or above
Desktop GPU rating (12th and 11th place)

Graphics Processing Unit

Base Clock 1660 MHz 1387 MHz
Boost Clock 2970 MHz 2394 MHz
Shading Units 4096 5376
Texture Mapping Units (TMUs) 256 336
Render Output Units (ROPs) 128 192
Compute Units (Pipelines) 64 -
Tensor Cores 128 -
Ray-tracing Cores 64 84
L1 Cache 128KB per cluster 256KB per cluster
L2 Cache 8MB shared 6MB shared
Instructions Per Cycle 4 IPC 4 IPC

Raw Performance

Pixel Fill Rate 380 GPixel/s 460 GPixel/s
Texture Fill Rate 760 GTexel/s 804 GTexel/s
FLOPS (FP32)
48.7 TFLOPS
51.5 TFLOPS

Physical

Interface PCIe 5.0 x16 PCIe 4.0 x16
TGP 304 W 300 W
Manufacturing TSMC TSMC
Fabrication Process 4 nm 5 nm
Die Size 357 mm² 529 mm²
Transistor Count 53.9 billion 57 billion
Transistor Density 150.98 MTr/mm² 107.75 MTr/mm²

Memory

Memory Type GDDR6 GDDR6
Memory Size 16 GB 20 GB
Memory Clock 2518 MHz 2500 MHz
Effective Memory Speed 20100 Mbps 20000 Mbps
Bus 256-bit 320-bit
ECC No No
Memory Bandwidth
644.6 GB/s
RX 7900 XT +24%
800 GB/s

API

DirectX 12.2 12
Vulkan 1.4 1.3
OpenGL 4.6 4.6
OpenCL 2.2 2.2
CUDA No -
Ray Tracing Yes Yes
DLSS No No
DisplayPort 2.1a 2.1

Cast your vote

Choose between two graphics cards
47 (39.5%)
72 (60.5%)
Total votes: 119

User opinions

You can share your opinion or ask a question in the comments below
🌐 Register your profile and become part of NanoReview community!
Avatar
Erik August 29, 2025 at 01:15 PM
The 7900XT is still a performance monster, undoubtedly one of the best, and a rare example of innovation in recent years. The chiplet architecture has brought many advantages, and it would have been right to push it further, but unfortunately AMD has abandoned the project. The 7900 XT and XTX remain exceptional GPUs, both in terms of pure geometry pass/raster performance and AI acceleration, and they also boast impressive memory configurations, making them longer-lasting than the competition, which now seems more interested on selling software updates than bringing hardware innovation, persisting the most vulgar anti-consumer policies and influencing the market with handsomely paid sponsorships. It's a shame that AMD hasn't yet brought these cards into the new generation, giving them the chance to express their true potential. I'm obviously talking about the software implementation of the new accelerators as well as support for FSR 4 which, contrary to what is said, is fully bearable by these unfairly (intentionally?) snubbed cards.
+25 Reply