NVIDIA RTX PRO 4000 Blackwell Mobile vs AMD Radeon HD 8670M
We compared two Mobile platform GPUs: 16GB VRAM RTX PRO 4000 Blackwell Mobile and 1024MB VRAM Radeon HD 8670M to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA RTX PRO 4000 Blackwell Mobile 's Advantages
Boost Clock has increased by 54% (1500MHz vs 975MHz)
More VRAM (16GB vs 1024GB)
Larger VRAM bandwidth (896.0GB/s vs 14.40GB/s)
7360 additional rendering cores
Score
Benchmark
FP32 (float)
RTX PRO 4000 Blackwell Mobile
+3592%
23.04 TFLOPS
Radeon HD 8670M
0.624 TFLOPS
Graphics Card
Unknown
Release Date
Mar 2013
Blackwell-MW
Generation
Solar System
Mobile
Type
Mobile
PCIe 5.0 x16
Bus Interface
PCIe 3.0 x8
Clock Speeds
975 MHz
Base Clock
925 MHz
1500 MHz
Boost Clock
975 MHz
1750 MHz
Memory Clock
900 MHz
Memory
16GB
Memory Size
1024MB
GDDR7
Memory Type
DDR3
256bit
Memory Bus
64bit
896.0GB/s
Bandwidth
14.40GB/s
Render Config
-
Compute Units
5
60
SM Count
-
7680
Shading Units
320
240
TMUs
20
96
ROPs
8
240
Tensor Cores
-
60
RT Cores
-
128 KB (per SM)
L1 Cache
16 KB (per CU)
64 MB
L2 Cache
128 KB
-
-
-
Theoretical Performance
144.0 GPixel/s
Pixel Rate
7.800 GPixel/s
360.0 GTexel/s
Texture Rate
19.50 GTexel/s
23.04 TFLOPS
FP16 (half)
-
23.04 TFLOPS
FP32 (float)
624.0 GFLOPS
360.0 GFLOPS
FP64 (double)
39.00 GFLOPS
Board Design
80W
TDP
Unknown
-
-
-
Portable Device Dependent
Outputs
Portable Device Dependent
None
Power Connectors
-
Graphics Processor
GB203
GPU Name
Sun
-
GPU Variant
Sun S3 XT
(216-0841009)
Blackwell 2.0
Architecture
GCN 1.0
TSMC
Foundry
TSMC
5 nm
Process Size
28 nm
45.6 billion
Transistors
0.69 billion
378 mm²
Die Size
56 mm²
Graphics Features
12 Ultimate (12_2)
DirectX
12 (11_1)
4.6
OpenGL
4.6
3.0
OpenCL
2.1 (1.2)
1.4
Vulkan
1.2.170
10.1
CUDA
-
6.8
Shader Model
6.5 (5.1)
