GPUs

EVGA GeForce RTX 3070 XC3 Ultra vs AMD Radeon RX 7900 GRE Full Specs

5,888 Shaders
1.77GHz
5,120 Shaders
2.25GHz
8GB GDDR6448GB/s
16GB GDDR6576GB/s
··
20.84 TFLOPS
··
45.98 TFLOPS
Form Factor
PCIe Card
Form Factor
PCIe Card
TDP
220W
TDP
260W
Power Connectors
-
Power Connectors
2x 8-Pin

GeForce RTX 3070 XC3 UltraGeForce RTX 3070 XC3 Ultra667 TOPSINT4 Tensor Sparse
x3.63
Radeon RX 7900 GRERadeon RX 7900 GRE183.9 TOPSINT4 Tensor
x1

Clock Speed
···
Clock Speed
···
Peak OPS
667 TOPSINT4 Tensor Sparse
Peak OPS
183.9 TOPSINT4 Tensor
Tensor FP16-16
83.37 TFLOPS
FP16-16 Tensor Sparse
166.7 TFLOPS
Tensor FP16-32
41.69 TFLOPS
FP16-32 Tensor Sparse
83.37 TFLOPS
Tensor FP16-16
45.98 TFLOPS
FP16-16 Tensor Sparse
-
Tensor FP16-32
45.98 TFLOPS
FP16-32 Tensor Sparse
-
BF16
20.84 TFLOPS
Tensor BF16
41.69 TFLOPS
BF16 Tensor Sparse
83.37 TFLOPS
BF16
91.96 TFLOPS
Tensor BF16
45.98 TFLOPS
BF16 Tensor Sparse
-
Tensor TF32
20.84 TFLOPS
Tensor TF32
-
FP32
20.84 TFLOPS
FP32
45.98 TFLOPS
FP64
325.7 GFLOPS
FP64
1.44 TFLOPS
Tensor INT4
333.5 TOPS
Tensor INT4
183.9 TOPS
Tensor INT8
166.7 TOPS
Tensor INT8
45.98 TOPS
Ray
31.44 TOPS
Ray
-
Pixel Rate
169.9 GPixel/s
Pixel Rate
359.2 GPixel/s
Texture Rate
325.7 GTexel/s
Texture Rate
718.4 GTexel/s

Shaders
5,888 Shaders
Shaders
5,120 Shaders
TMUs
184 TMUs
TMUs
320 TMUs
ROPs
96 ROPs
ROPs
160 ROPs
Tensor Cores
184 T-Cores
Tensor Cores
160 T-Cores
RT Cores
46 RT-Cores
RT Cores
80 RT-Cores
SMs
46 SMs
CUs
80 CUs

Base Clock
1.5GHz
Base Clock
1.88GHz
Boost Clock
1.77GHz
Boost Clock
2.25GHz

L2 Cache
4.1MB shared
L2 Cache
6.1MB shared
L3 Cache
-
L3 Cache
64MB shared
L3 Bandwidth
-
L3 Bandwidth
2.25TB/s

8GB GDDR6
16GB GDDR6
Memory Bus
256-bit
Memory Bus
256-bit
Memory Speed
14GT/s
Memory Speed
18GT/s
Memory Bandwidth
448GB/s
Memory Bandwidth
576GB/s

TDP
220W
TDP
260W
Max Temp
93°C Max
Max Temp
-

Multi-Monitor
4
Multi-Monitor
3
HDCP
HDCP 2.3
HDCP
HDCP 2.3

-
2x DisplayPort 2.1
3x DisplayPort 1.4
-
1x HDMI 2.1
1x HDMI 2.1
-
1x USB-C

Encoder Model
NVENC 7
Encoder Model
VCN 4.0

Decoder Model
NVDEC 5
Decoder Model
VCN 4.0

Form Factor
PCIe Card
Form Factor
PCIe Card
PCIe
2.1-Slots
PCIe
2.5-Slots
Height
111.2 mm (4.38")
Width
285.4 mm (11.24")
Depth
43 mm (1.69")
Height
110 mm (4.33")
Width
276 mm (10.87")
Depth
51 mm (2.01")
Cooling
Open-Air
3x Fans
Cooling
Open-Air
3x Fans
Power Connectors
-
Power Connectors
2x 8-Pin

Manufacturer
Manufacturer
Chip Designer
Chip Designer
Architecture
Architecture
Family
Family
Branding
GeForce RTX 2018 branding
Branding
Radeon 2023 branding
Codename
NV174
Codename
Plum Bonito
Chip Variant
GA104-150-A1
Chip Variant
Navi 31 XL
Market Segment
Desktop
Market Segment
Desktop
Release Date
Oct 29, 2020
Release Date
Jul 27, 2023

Foundry
Samsung
Foundry
TSMC
Other Foundries
-
Other Foundries
TSMCMCD
Fabrication Node
8N
-
Fabrication Node
N5
N6MCD
Die Size
393mm²
-
Die Size
304mm²
150mm²MCD
Transistor Count
17.4 Billion
-
Transistor Count
45.4 Billion
8.2 BillionMCD
Transistor Density
44.33 MTr/mm²
-
Transistor Density
149.2 MTr/mm²
54.67 MTr/mm²MCD

No images available
No images available