GPU Comparison
RADEON
AMD Radeon Pro W6800X
CORE STATE
Navi 21
VRAM
32 GB
CLOCK SPEED
2087 MHz
TDP
200 W
BUS WIDTH
256 bit
ARCHITECTURE
RDNA 2.0
PROCESS
7 nm
LAUNCH DATE
2021
VS
GEFORCE
B200
CORE STATE
GB100
VRAM
90 GB
CLOCK SPEED
1965 MHz
TDP
1000 W
BUS WIDTH
4096 bit
ARCHITECTURE
Blackwell
PROCESS
5 nm
LAUNCH DATE
—
PERFORMANCE BENCHMARKS
geekbench_metal
geekbench_opencl
DETAILED SPECIFICATIONS
SPECIFICATION
Pro W6800X
B200
Core Specs
Shading Units
3,840
18,944
+393.3%
Shaders
3,840
18,944
+393.3%
TMUs
240
592
+146.7%
ROPs
96
24
-75.0%
Compute Units
60
—
SM Count
—
148
Clocks
Base Clock
1800 MHz
700 MHz
Boost Clock
2087 MHz
1965 MHz
Memory Clock
2000 MHz
16 Gbps effective
2000 MHz
8 Gbps effective
Memory
Memory Size
32 GB
90 GB
VRAM (MB)
32,768
92,160
+181.3%
Memory Type
GDDR6
HBM3e
Memory Bus
256 bit
4096 bit
Bandwidth
512.0 GB/s
4.10 TB/s
Cache
L1 Cache
128 KB per Array
256 KB (per SM)
L2 Cache
4 MB
50 MB
L3 Cache
128 MB
—
L0 Cache
32 KB per WGP
—
Performance
Pixel Rate
200.4 GPixel/s
47.16 GPixel/s
Texture Rate
500.9 GTexel/s
1,163.3 GTexel/s
FP32 (TFLOPS)
16.03 TFLOPS
74.45 TFLOPS
FP64 (TFLOPS)
1,001.8 GFLOPS (1:16)
37.22 TFLOPS (1:2)
FP16 (TFLOPS)
32.06 TFLOPS (2:1)
1,191.2 TFLOPS (16:1)
AI/RT
RT Cores
60
—
Tensor Cores
—
592
Power
TDP
200 W
1000 W
TDP (W)
200
1,000
+400.0%
Suggested PSU
550 W
1400 W
Power Connectors
Apple MPX
—
Architecture
Architecture
RDNA 2.0
Blackwell
GPU Name
Navi 21
GB100
Generation
Radeon Pro Mac
(Navi II Series)
Server Blackwell
(Bxx)
Process Size
7 nm
5 nm
Transistors
26,800 million
104,000 million
Die Size
520 mm²
—
Foundry
TSMC
TSMC
Density
51.5M / mm²
—
API Support
DirectX
12 Ultimate (12_2)
—
OpenGL
4.6
—
Vulkan
1.4
—
OpenCL
2.1
3.0
CUDA
—
10.0
Shader Model
6.8
—
Physical
Slot Width
Quad-slot
SXM Module
Length
267 mm
10.5 inches
—
Height
120 mm
4.7 inches
—
Outputs
1x HDMI 2.14x Thunderbolt
No outputs
Bus Interface
Apple MPX
PCIe 5.0 x16
Other
Launch Price
2,799 USD
—
Production
End-of-life
Active
Predecessor
—
Server Hopper
Successor
—
Server Rubin