GPU Comparison
RADEON
AMD Radeon 680M
CORE STATE
Rembrandt+
VRAM
System Shared
CLOCK SPEED
2200 MHz
TDP
50 W
BUS WIDTH
System Shared
ARCHITECTURE
RDNA 2.0
PROCESS
6 nm
LAUNCH DATE
2023
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
3dmark_3dmark_steel_nomad_dx12
geekbench_opencl
geekbench_vulkan
DETAILED SPECIFICATIONS
SPECIFICATION
680M
B200
Core Specs
Shading Units
768
18,944
+2366.7%
Shaders
768
18,944
+2366.7%
TMUs
48
592
+1133.3%
ROPs
32
24
-25.0%
Compute Units
12
—
SM Count
—
148
Clocks
Base Clock
2000 MHz
700 MHz
Boost Clock
2200 MHz
1965 MHz
Memory Clock
System Shared
2000 MHz
8 Gbps effective
Memory
Memory Size
System Shared
90 GB
VRAM (MB)
—
92,160
Memory Type
System Shared
HBM3e
Memory Bus
System Shared
4096 bit
Bandwidth
System Dependent
4.10 TB/s
Cache
L1 Cache
128 KB per Array
256 KB (per SM)
L2 Cache
2 MB
50 MB
L0 Cache
32 KB per WGP
—
Performance
Pixel Rate
70.40 GPixel/s
47.16 GPixel/s
Texture Rate
105.6 GTexel/s
1,163.3 GTexel/s
FP32 (TFLOPS)
3.379 TFLOPS
74.45 TFLOPS
FP64 (TFLOPS)
211.2 GFLOPS (1:16)
37.22 TFLOPS (1:2)
FP16 (TFLOPS)
6.758 TFLOPS (2:1)
1,191.2 TFLOPS (16:1)
AI/RT
RT Cores
12
—
Tensor Cores
—
592
Power
TDP
50 W
1000 W
TDP (W)
50
1,000
+1900.0%
Suggested PSU
—
1400 W
Power Connectors
None
—
Architecture
Architecture
RDNA 2.0
Blackwell
GPU Name
Rembrandt+
GB100
Generation
Navi II IGP
(Rembrandt Mobile)
Server Blackwell
(Bxx)
Process Size
6 nm
5 nm
Transistors
13,100 million
104,000 million
Die Size
208 mm²
—
Foundry
TSMC
TSMC
Density
63.0M / mm²
—
API Support
DirectX
12 Ultimate (12_2)
—
OpenGL
4.6
—
Vulkan
1.4
—
OpenCL
2.0
3.0
CUDA
—
10.0
Shader Model
6.8
—
Physical
Slot Width
IGP
SXM Module
Outputs
Portable Device Dependent
No outputs
Bus Interface
PCIe 4.0 x8
PCIe 5.0 x16
Other
Production
Active
Active
Predecessor
Vega II IGP
Server Hopper
Successor
Navi III IGP
Server Rubin