GeForce GTX 660 Ti vs Radeon Instinct MI350X
We compared two Desktop platform GPUs: 2GB VRAM GeForce GTX 660 Ti and 288GB VRAM Radeon Instinct MI350X to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
GeForce GTX 660 Ti 's Advantages
Lower TDP (150W vs 1000W)
Radeon Instinct MI350X 's Advantages
Released 12 years and 5 months late
Boost Clock has increased by 124% (2200MHz vs 980MHz)
More VRAM (288GB vs 2GB)
Larger VRAM bandwidth (8.19TB/s vs 144.2GB/s)
15040 additional rendering cores
Score
Benchmark
FP32 (float)
GeForce GTX 660 Ti
2634
Radeon Instinct MI350X
+2636%
72090
Graphics Card
Aug 2012
Release Date
Jan 2025
GeForce 600
Generation
Radeon Instinct
Desktop
Type
Desktop
PCIe 3.0 x16
Bus Interface
PCIe 5.0 x16
Clock Speeds
915 MHz
Base Clock
1000 MHz
980 MHz
Boost Clock
2200 MHz
1502 MHz
Memory Clock
2000 MHz
Memory
2GB
Memory Size
288GB
GDDR5
Memory Type
HBM3e
192bit
Memory Bus
8192bit
144.2GB/s
Bandwidth
8.19TB/s
Render Config
-
Compute Units
256
1344
Shading Units
16384
112
TMUs
1024
24
ROPs
0
-
Tensor Cores
1024
16 KB (per SMX)
L1 Cache
16 KB (per CU)
384 KB
L2 Cache
16 MB
-
L3 Cache
256 MB
Theoretical Performance
27.44 GPixel/s
Pixel Rate
0 MPixel/s
109.8 GTexel/s
Texture Rate
2252.8 GTexel/s
-
FP16 (half)
576.7 TFLOPS
2.634 TFLOPS
FP32 (float)
72.09 TFLOPS
109.8 GFLOPS
FP64 (double)
72.09 TFLOPS
Board Design
150W
TDP
1000W
450 W
Suggested PSU
1400 W
2x DVI
1x HDMI 1.4a
1x DisplayPort 1.2
Outputs
No outputs
2x 6-pin
Power Connectors
None
Graphics Processor
GK104
GPU Name
CDNA Next
GK104-300-KD-A2
GPU Variant
-
Kepler
Architecture
CDNA 4.0
TSMC
Foundry
TSMC
28 nm
Process Size
3 nm
3.54 billion
Transistors
185 billion
294 mm²
Die Size
1017 mm²
Graphics Features
12 (11_0)
DirectX
N/A
4.6
OpenGL
N/A
3.0
OpenCL
3.0
1.1
Vulkan
N/A
3.0
CUDA
-
5.1
Shader Model
N/A