GeForce RTX 5090 vs Radeon HD 3850 X2
We compared two Desktop platform GPUs: 32GB VRAM GeForce RTX 5090 and 512MB VRAM Radeon HD 3850 X2 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
GeForce RTX 5090 's Advantages
Released 16 years and 9 months late
Boost Clock2407MHz
More VRAM (32GB vs 512GB)
Larger VRAM bandwidth (1.79TB/s vs 52.99GB/s)
21440 additional rendering cores
Radeon HD 3850 X2 's Advantages
Lower TDP (140W vs 575W)
Score
Benchmark
FP32 (float)
GeForce RTX 5090
+24385%
104800
Radeon HD 3850 X2
428
Graphics Card
Jan 2025
Release Date
Apr 2008
GeForce 50
Generation
Radeon R600
Desktop
Type
Desktop
PCIe 5.0 x16
Bus Interface
PCIe 2.0 x16
Clock Speeds
2017 MHz
Base Clock
-
2407 MHz
Boost Clock
-
1750 MHz
Memory Clock
828 MHz
Memory
32GB
Memory Size
512MB
GDDR7
Memory Type
GDDR3
512bit
Memory Bus
256bit
1.79TB/s
Bandwidth
52.99GB/s
Render Config
-
Compute Units
4
170
SM Count
-
21760
Shading Units
320
680
TMUs
16
176
ROPs
16
680
Tensor Cores
-
170
RT Cores
-
128 KB (per SM)
L1 Cache
-
96 MB
L2 Cache
256 KB
Theoretical Performance
423.6 GPixel/s
Pixel Rate
10.70 GPixel/s
1637 GTexel/s
Texture Rate
10.70 GTexel/s
104.8 TFLOPS
FP16 (half)
-
104.8 TFLOPS
FP32 (float)
428.2 GFLOPS
1.637 TFLOPS
FP64 (double)
85.63 GFLOPS
Board Design
575W
TDP
140W
950 W
Suggested PSU
300 W
1x HDMI 2.1b
3x DisplayPort 2.1b
Outputs
2x DVI
1x S-Video
1x 16-pin
Power Connectors
-
Graphics Processor
GB202
GPU Name
RV670
GB202-300-A1
GPU Variant
RV670 PRO
(215-0708003)
Blackwell 2.0
Architecture
TeraScale
TSMC
Foundry
TSMC
5 nm
Process Size
55 nm
92.2 billion
Transistors
0.666 billion
750 mm²
Die Size
192 mm²
Graphics Features
12 Ultimate (12_2)
DirectX
10.1 (10_1)
4.6
OpenGL
3.3 (full)
4.0 (partial)
3.0
OpenCL
N/A
1.4
Vulkan
N/A
12.0
CUDA
-
6.8
Shader Model
4.1