AMD Radeon RX 7650 GRE vs NVIDIA 6x GeForce RTX 5090
AMD Radeon RX 7650 GRE
$279
NVIDIA 6x GeForce RTX 5090
$11,994
|
2048 Shaders
8GB GDDR6
2695MHz
|
6x 21760 Shaders
192GB (6x 32GB) GDDR7
2407MHz
|
|
Peak AI Performance
88.31 TOPS
INT4 Tensor
|
Peak AI Performance
20.11 PFLOPS
FP4 Tensor Sparse
|
|
FP32
22.08 TFLOPS
|
FP32
628.52 TFLOPS
|
|
FP16
44.15 TFLOPS
|
FP16
628.52 TFLOPS
|
|
Form Factor
PCIe Card
2.0-Slots
|
Form Factor
PCIe Card
6x 2.1-Slots
|
|
TDP
165W
|
TDP
3450W
|
|
Power Connectors
-
1x 8-Pin
-
-
|
Power Connectors
-
-
-
1x 16-Pin 12VHPWR
|
|
GB6 OpenCL N/A
0%
|
GB6 OpenCL N/A
0%
|
|
GB6 Metal N/A
0%
|
GB6 Metal N/A
0%
|
|
GB6 Vulkan N/A
0%
|
GB6 Vulkan N/A
0%
|
|
GB5 OpenCL N/A
0%
|
GB5 OpenCL N/A
0%
|
|
GB5 CUDA N/A
0%
|
GB5 CUDA N/A
0%
|
|
GB5 Metal N/A
0%
|
GB5 Metal N/A
0%
|
|
GB5 Vulkan N/A
0%
|
GB5 Vulkan N/A
0%
|
|
OCT 2020.1 N/A
0%
|
OCT 2020.1 N/A
0%
|
|
OCT Metal N/A
0%
|
OCT Metal N/A
0%
|
|
Peak AI
Performance
88.31 TOPS
INT4 Tensor
|
Peak AI
Performance
20.11 PFLOPS
FP4 Tensor Sparse
|
|
-
-
-
|
FP4
10.06 PFLOPS
Tensor
20.11 PFLOPS
Tensor Sparse
|
|
-
-
-
-
-
-
|
FP8
-
5.03 PFLOPS
Tensor (FP16 Accumulate)
10.06 PFLOPS
Tensor (FP16 Accumulate) Sparse
2.51 PFLOPS
Tensor (FP32 Accumulate)
5.03 PFLOPS
Tensor (FP32 Accumulate) Sparse
|
|
FP16
44.15 TFLOPS
22.08 TFLOPS
Tensor (FP16 Accumulate)
-
22.08 TFLOPS
Tensor (FP32 Accumulate)
-
|
FP16
628.52 TFLOPS
2.51 PFLOPS
Tensor (FP16 Accumulate)
5.03 PFLOPS
Tensor (FP16 Accumulate) Sparse
1.26 PFLOPS
Tensor (FP32 Accumulate)
2.51 PFLOPS
Tensor (FP32 Accumulate) Sparse
|
|
FP32
22.08 TFLOPS
-
-
|
FP32
628.52 TFLOPS
-
-
|
|
FP64
690 GFLOPS
-
|
FP64
9.82 TFLOPS
-
|
|
BF16
44.15 TFLOPS
22.08 TFLOPS
Tensor
-
|
BF16
628.52 TFLOPS
1.26 PFLOPS
Tensor
2.51 PFLOPS
Tensor Sparse
|
|
-
-
-
|
TF32
628.52 TFLOPS
Tensor
1.26 PFLOPS
Tensor Sparse
|
|
INT4
88.31 TOPS
Tensor
-
|
-
-
-
|
|
INT8
-
22.08 TOPS
Tensor
-
|
INT8
-
5.03 POPS
Tensor
10.06 POPS
Tensor Sparse
|
|
INT32
11.04 TOPS
|
INT32
628.52 TOPS
|
|
-
-
|
Ray Tracing
317.7 TOPS
|
|
Pixel
Fillrate
172.48 GPixel/s
|
Pixel
Fillrate
423.632 GPixel/s
|
|
-
-
|
-
-
|
|
Texture
Fillrate
344.96 GTexel/s
|
Texture
Fillrate
1636.76 GTexel/s
|
|
Manufacturer
AMD
|
Manufacturer
NVIDIA
|
|
Chip Designer
AMD
|
Chip Designer
NVIDIA
|
|
Architecture
RDNA 3
|
Architecture
Blackwell
|
|
Family
Radeon RX 7000
|
Family
GeForce 50
|
|
Codename
Hotpink Bonefish
Navi 33
Variant
Navi 33 XL
|
Codename
NV192
GB202
Variant
GB202-300-A1
|
|
Market Segment
Desktop
|
Market Segment
Desktop
|
|
Release Date
2/26/2025
|
Release Date
1/6/2025
|
|
Foundry
TSMC
-
|
Foundry
TSMC
-
|
|
Fabrication Node
N6
-
|
Fabrication Node
4NP
-
|
|
Die Size
204 mm²
-
|
Die Size
6x 762 mm²
-
|
|
Transistor Count
13.3 Billion
-
|
Transistor Count
6x 92.2 Billion
-
|
|
Transistor Density
65.20M/mm²
-
|
Transistor Density
121.07M/mm²
-
|
|
Form
PCIe Card
|
Form
PCIe Card
|
|
Shading Units
2048 Shaders
-
|
Shading Units
6x 21760 Shaders
-
|
|
Texture Mapping Units
128 TMUs
|
Texture Mapping Units
6x 680 TMUs
|
|
Render Output Units
64 ROPs
|
Render Output Units
6x 176 ROPs
|
|
Tensor Cores
64 T-Cores
|
Tensor Cores
6x 680 T-Cores
|
|
Ray-Tracing Cores
32 RT-Cores
|
Ray-Tracing Cores
6x 170 RT-Cores
|
|
-
-
|
Streaming Multiprocessors
6x 170 SMs
|
|
Compute Units
32 CUs
|
-
-
|
|
-
-
|
-
-
|
|
-
-
|
Graphics Processing Clusters
6x 11 GPCs
|
|
-
-
1720MHz Base
2695MHz
|
-
-
2010MHz Base
2407MHz
|
|
L0
64KB/WGP
|
-
-
|
|
L1
-
-
-
256KB/Array
|
L1
64KB/SM Tex
128KB/SM
-
-
|
|
L2
2MB Shared
|
L2
96MB Shared
|
|
L3
32MB Shared
1.16TB/s
|
-
-
-
|
|
8GB
GDDR6
-
|
192GB (6x 32GB)
GDDR7
-
|
|
Bus Width
128Bit
|
Bus Width
512Bit
|
|
Clock
2250MHz
Transfer Rate
18GT/s
Bandwidth
288GB/s
|
Clock
1750MHz
Transfer Rate
28GT/s
Bandwidth
1792GB/s
|
|
-
-
-
-
-
-
-
-
-
|
-
-
-
-
-
-
-
-
-
|
|
TDP
165W
|
TDP
3450W
|
|
-
-
|
Temp
90°C Max
|
|
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
3x DisplayPort 2.1
-
-
-
-
-
-
-
-
-
1x HDMI 2.1
-
-
|
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
18x DisplayPort 2.1
-
-
-
-
-
-
-
-
-
6x HDMI 2.1
-
-
|
|
Max Resolution
15360x8640
|
Max Resolution
7680x4320
|
|
Max Resolution Refresh Rate
165Hz
|
Max Resolution Refresh Rate
165Hz
|
|
Variable Refresh Rate
-
FreeSync
-
|
Variable Refresh Rate
G-Sync
FreeSync
-
|
|
Display Stream Compression (DSC)
Supported
|
Display Stream Compression (DSC)
Supported
|
|
Multi Monitor Support
3
|
Multi Monitor Support
4
|
|
Content Protection
HDCP 2.3
|
Content Protection
HDCP 2.3
|
|
Model
VCN 4.0
|
Model
3x NVENC 9
|
|
Codec
-
-
-
-
-
-
VP9
-
AVC (H.264)
HEVC (H.265)
-
AV1
-
-
|
Codec
-
-
-
-
-
-
-
-
AVC (H.264)
HEVC (H.265)
-
AV1
-
-
|
|
Model
VCN 4.0
|
Model
2x NVDEC 6
|
|
Codec
MPEG-1
MPEG-2
MPEG-4
JPEG
VC-1
-
VP9
-
AVC (H.264)
HEVC (H.265)
-
AV1
-
-
|
Codec
MPEG-1
MPEG-2
MPEG-4
-
VC-1
VP8
VP9
-
AVC (H.264)
HEVC (H.265)
-
AV1
-
-
|
|
Direct X
12
Direct 3D
12_2
|
Direct X
12
Direct 3D
12_3
|
|
OpenGL
4.6
OpenCL
2.2
Vulkan
1.3
|
OpenGL
4.6
OpenCL
3.0
Vulkan
1.3
|
|
Shader Model
6.7
-
-
GFX
11
-
-
-
-
|
Shader Model
6.8
CUDA
12.8
-
-
PureVideo HD
VP13
VDPAU
Feature Set M
|
|
-
-
-
2x Fans
|
-
-
-
2x Fans
|
|
Power Connectors
-
-
-
1x 8-Pin
-
-
-
|
Power Connectors
-
-
-
-
-
-
1x 16-Pin 12VHPWR
|
|
Slots Required
2.0
PCIe Version
4.0
PCIe Lanes
8
|
Slots Required
2.1
PCIe Version
5.0
PCIe Lanes
16
|
|
Multi GPU Support
Supported
Type
CrossFire XDMA
|
-
-
-
-
|
|
Height
115 mm (4.53 in)
Width
204 mm (8.03 in)
Depth
40 mm (1.57 in)
|
Height
137 mm (5.39 in)
Width
304 mm (11.97 in)
Depth
42 mm (1.65 in)
|
Copy Link