GPU Comparison
RADEON
AMD Radeon PRO W6400
CORE STATE
Navi 24
VRAM
4 GB
CLOCK SPEED
2321 MHz
TDP
50 W
BUS WIDTH
64 bit
ARCHITECTURE
RDNA 2.0
PROCESS
6 nm
LAUNCH DATE
2022
VS
GEFORCE
H200 NVL
CORE STATE
GH100
VRAM
141 GB
CLOCK SPEED
1785 MHz
TDP
600 W
BUS WIDTH
6144 bit
ARCHITECTURE
Hopper
PROCESS
5 nm
LAUNCH DATE
2024
PERFORMANCE BENCHMARKS
geekbench_opencl
DETAILED SPECIFICATIONS
SPECIFICATION
PRO W6400
H200 NVL
Core Specs
Shading Units
768
16,896
+2100.0%
Shaders
768
16,896
+2100.0%
TMUs
48
528
+1000.0%
ROPs
32
24
-25.0%
Compute Units
12
—
SM Count
—
132
Clocks
Base Clock
2039 MHz
1365 MHz
Boost Clock
2321 MHz
1785 MHz
Memory Clock
2000 MHz
16 Gbps effective
1593 MHz
6.4 Gbps effective
Memory
Memory Size
4 GB
141 GB
VRAM (MB)
4,096
144,384
+3425.0%
Memory Type
GDDR6
HBM3e
Memory Bus
64 bit
6144 bit
Bandwidth
128.0 GB/s
4.89 TB/s
Cache
L1 Cache
128 KB per Array
256 KB (per SM)
L2 Cache
1024 KB
50 MB
L3 Cache
8 MB
—
L0 Cache
32 KB per WGP
—
Performance
Pixel Rate
74.27 GPixel/s
42.84 GPixel/s
Texture Rate
111.4 GTexel/s
942.5 GTexel/s
FP32 (TFLOPS)
3.565 TFLOPS
60.32 TFLOPS
FP64 (TFLOPS)
222.8 GFLOPS (1:16)
30.16 TFLOPS (1:2)
FP16 (TFLOPS)
7.130 TFLOPS (2:1)
241.3 TFLOPS (4:1)
AI/RT
RT Cores
12
—
Tensor Cores
—
528
Power
TDP
50 W
600 W
TDP (W)
50
600
+1100.0%
Suggested PSU
250 W
1000 W
Power Connectors
None
8-pin EPS
Architecture
Architecture
RDNA 2.0
Hopper
GPU Name
Navi 24
GH100
Generation
Radeon Pro Navi
(Navi II Series)
Server Hopper
(Hxx)
Process Size
6 nm
5 nm
Transistors
5,400 million
80,000 million
Die Size
107 mm²
814 mm²
Foundry
TSMC
TSMC
Density
50.5M / mm²
98.3M / mm²
API Support
DirectX
12 Ultimate (12_2)
—
OpenGL
4.6
—
Vulkan
1.4
—
OpenCL
2.2
3.0
CUDA
—
9.0
Shader Model
6.8
—
Physical
Slot Width
Single-slot
Dual-slot
Length
—
267 mm
10.5 inches
Height
—
111 mm
4.4 inches
Outputs
2x DisplayPort 1.4a
No outputs
Bus Interface
PCIe 4.0 x4
PCIe 5.0 x16
Other
Production
End-of-life
Active
Predecessor
Radeon Pro Vega
Server Ada
Successor
—
Server Blackwell