GPU Comparison
RADEON
AMD Stream Processor
CORE STATE
R580
VRAM
1024 MB
CLOCK SPEED
—
TDP
165 W
BUS WIDTH
256 bit
ARCHITECTURE
Ultra-Threaded SE
PROCESS
90 nm
LAUNCH DATE
—
VS
GEFORCE
GeForce RTX 4070 GDDR6
CORE STATE
AD104
VRAM
12 GB
CLOCK SPEED
2475 MHz
TDP
200 W
BUS WIDTH
192 bit
ARCHITECTURE
Ada Lovelace
PROCESS
5 nm
LAUNCH DATE
2024
DETAILED SPECIFICATIONS
SPECIFICATION
Stream Processor
RTX 4070 GDDR6
Core Specs
Shading Units
—
5,888
Shaders
—
5,888
TMUs
16
184
+1050.0%
ROPs
16
64
+300.0%
SM Count
—
46
Clocks
Base Clock
—
1920 MHz
Boost Clock
—
2475 MHz
GPU Clock
594 MHz
—
Memory Clock
648 MHz
1296 Mbps effective
2500 MHz
20 Gbps effective
Memory
Memory Size
1024 MB
12 GB
VRAM (MB)
1,024
12,288
+1100.0%
Memory Type
GDDR3
GDDR6
Memory Bus
256 bit
192 bit
Bandwidth
41.47 GB/s
480.0 GB/s
Cache
L1 Cache
—
128 KB (per SM)
L2 Cache
—
36 MB
Performance
Pixel Rate
9.504 GPixel/s
158.4 GPixel/s
Texture Rate
9.504 GTexel/s
455.4 GTexel/s
FP32 (TFLOPS)
—
29.15 TFLOPS
FP64 (TFLOPS)
—
455.4 GFLOPS (1:64)
FP16 (TFLOPS)
—
29.15 TFLOPS (1:1)
AI/RT
RT Cores
—
46
Tensor Cores
—
184
Power
TDP
165 W
200 W
TDP (W)
165
200
+21.2%
Suggested PSU
450 W
550 W
Power Connectors
1x 6-pin
1x 16-pin
Architecture
Architecture
Ultra-Threaded SE
Ada Lovelace
GPU Name
R580
AD104
Generation
FireStream
GeForce 40
Process Size
90 nm
5 nm
Transistors
384 million
35,800 million
Die Size
352 mm²
294 mm²
Foundry
TSMC
TSMC
Density
1.1M / mm²
121.8M / mm²
API Support
DirectX
9.0c (9_3)
12 Ultimate (12_2)
OpenGL
2.1 (full)
3.0 (partial)
4.6
Vulkan
—
1.4
OpenCL
—
3.0
CUDA
—
8.9
Shader Model
3.0
6.8
Physical
Slot Width
Dual-slot
Dual-slot
Length
241 mm
9.5 inches
240 mm
9.4 inches
Height
111 mm
4.4 inches
110 mm
4.3 inches
Outputs
2x DVI1x S-Video
1x HDMI 2.13x DisplayPort 1.4a
Bus Interface
PCIe 1.0 x16
PCIe 4.0 x16
Other
Launch Price
—
599 USD
Production
End-of-life
End-of-life
Predecessor
Rage GL
GeForce 30
Successor
FireGL
GeForce 50