GeForce RTX 5070 vs Radeon R9 370 1024SP
We compared two Desktop platform GPUs: 12GB VRAM GeForce RTX 5070 and 2GB VRAM Radeon R9 370 1024SP to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
GeForce RTX 5070 's Advantages
Released 9 years and 9 months late
Boost Clock has increased by 158% (2512MHz vs 975MHz)
More VRAM (12GB vs 2GB)
Larger VRAM bandwidth (672.0GB/s vs 179.2GB/s)
5120 additional rendering cores
Radeon R9 370 1024SP 's Advantages
Lower TDP (150W vs 250W)
Score
Benchmark
FP32 (float)
GeForce RTX 5070
+1445%
30870
Radeon R9 370 1024SP
1997
Graphics Card
Mar 2025
Release Date
Jun 2015
GeForce 50
Generation
Pirate Islands
Desktop
Type
Desktop
PCIe 5.0 x16
Bus Interface
PCIe 3.0 x16
Clock Speeds
2325 MHz
Base Clock
925 MHz
2512 MHz
Boost Clock
975 MHz
1750 MHz
Memory Clock
1400 MHz
Memory
12GB
Memory Size
2GB
GDDR7
Memory Type
GDDR5
192bit
Memory Bus
256bit
672.0GB/s
Bandwidth
179.2GB/s
Render Config
-
Compute Units
16
48
SM Count
-
6144
Shading Units
1024
192
TMUs
64
80
ROPs
32
192
Tensor Cores
-
48
RT Cores
-
128 KB (per SM)
L1 Cache
16 KB (per CU)
48 MB
L2 Cache
512 KB
Theoretical Performance
201.0 GPixel/s
Pixel Rate
31.20 GPixel/s
482.3 GTexel/s
Texture Rate
62.40 GTexel/s
30.87 TFLOPS
FP16 (half)
-
30.87 TFLOPS
FP32 (float)
1.997 TFLOPS
482.3 GFLOPS
FP64 (double)
124.8 GFLOPS
Board Design
250W
TDP
150W
600 W
Suggested PSU
450 W
1x HDMI 2.1b
3x DisplayPort 2.1b
Outputs
2x DVI
1x HDMI 1.4a
1x DisplayPort 1.2
1x 16-pin
Power Connectors
1x 6-pin
Graphics Processor
GB205
GPU Name
Trinidad
GB205-300-A1
GPU Variant
Trinidad PRO
(215-0870020)
Blackwell 2.0
Architecture
GCN 1.0
TSMC
Foundry
TSMC
5 nm
Process Size
28 nm
31.1 billion
Transistors
2.8 billion
263 mm²
Die Size
212 mm²
Graphics Features
12 Ultimate (12_2)
DirectX
12 (11_1)
4.6
OpenGL
4.6
3.0
OpenCL
1.2
1.4
Vulkan
1.2
10.1
CUDA
-
6.8
Shader Model
5.1