GeForce GTX 970 vs Radeon HD 4890
We compared two Desktop platform GPUs: 4GB VRAM GeForce GTX 970 and 1024MB VRAM Radeon HD 4890 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
GeForce GTX 970 's Advantages
Released 5 years and 5 months late
Boost Clock1178MHz
More VRAM (4GB vs 1024GB)
Larger VRAM bandwidth (224.4GB/s vs 124.8GB/s)
864 additional rendering cores
Lower TDP (148W vs 190W)
Score
Benchmark
FP32 (float)
GeForce GTX 970
+188%
3920
Radeon HD 4890
1360
Graphics Card
Sep 2014
Release Date
Apr 2009
GeForce 900
Generation
Radeon R700
Desktop
Type
Desktop
PCIe 3.0 x16
Bus Interface
PCIe 2.0 x16
Clock Speeds
1050 MHz
Base Clock
-
1178 MHz
Boost Clock
-
1753 MHz
Memory Clock
975 MHz
Memory
4GB
Memory Size
1024MB
GDDR5
Memory Type
GDDR5
256bit
Memory Bus
256bit
224.4GB/s
Bandwidth
124.8GB/s
Render Config
-
Compute Units
10
1664
Shading Units
800
104
TMUs
40
56
ROPs
16
48 KB (per SMM)
L1 Cache
16 KB (per CU)
2 MB
L2 Cache
256 KB
Theoretical Performance
65.97 GPixel/s
Pixel Rate
13.60 GPixel/s
122.5 GTexel/s
Texture Rate
34.00 GTexel/s
3.920 TFLOPS
FP32 (float)
1360 GFLOPS
122.5 GFLOPS
FP64 (double)
272.0 GFLOPS
Board Design
148W
TDP
190W
300 W
Suggested PSU
450 W
1x DVI
1x HDMI 2.0
3x DisplayPort 1.4a
Outputs
2x DVI
1x S-Video
2x 6-pin
Power Connectors
2x 6-pin
Graphics Processor
GM204
GPU Name
RV790
GM204-200-A1
GPU Variant
RV790 XT
(215-0758016)
Maxwell 2.0
Architecture
TeraScale
TSMC
Foundry
TSMC
28 nm
Process Size
55 nm
5.2 billion
Transistors
0.959 billion
398 mm²
Die Size
282 mm²
Graphics Features
12 (12_1)
DirectX
10.1 (10_1)
4.6
OpenGL
3.3
3.0
OpenCL
1.1
1.3
Vulkan
N/A
5.2
CUDA
-
6.4
Shader Model
4.1
