GPU Comparison
GEFORCE
NVIDIA GeForce MX330
CORE STATE
GP108B
VRAM
2 GB
CLOCK SPEED
1594 MHz
TDP
10 W
BUS WIDTH
64 bit
ARCHITECTURE
Pascal
PROCESS
14 nm
LAUNCH DATE
2020
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
geekbench_vulkan
DETAILED SPECIFICATIONS
SPECIFICATION
MX330
H200 NVL
Core Specs
Shading Units
384
16,896
+4300.0%
Shaders
384
16,896
+4300.0%
TMUs
24
528
+2100.0%
ROPs
16
24
+50.0%
SM Count
3
132
+4300.0%
Clocks
Base Clock
1531 MHz
1365 MHz
Boost Clock
1594 MHz
1785 MHz
Memory Clock
1752 MHz
7 Gbps effective
1593 MHz
6.4 Gbps effective
Memory
Memory Size
2 GB
141 GB
VRAM (MB)
2,048
144,384
+6950.0%
Memory Type
GDDR5
HBM3e
Memory Bus
64 bit
6144 bit
Bandwidth
56.06 GB/s
4.89 TB/s
Cache
L1 Cache
48 KB (per SM)
256 KB (per SM)
L2 Cache
512 KB
50 MB
Performance
Pixel Rate
25.50 GPixel/s
42.84 GPixel/s
Texture Rate
38.26 GTexel/s
942.5 GTexel/s
FP32 (TFLOPS)
1,224.2 GFLOPS
60.32 TFLOPS
FP64 (TFLOPS)
38.26 GFLOPS (1:32)
30.16 TFLOPS (1:2)
FP16 (TFLOPS)
19.13 GFLOPS (1:64)
241.3 TFLOPS (4:1)
AI/RT
Tensor Cores
—
528
Power
TDP
10 W
600 W
TDP (W)
10
600
+5900.0%
Suggested PSU
—
1000 W
Power Connectors
None
8-pin EPS
Architecture
Architecture
Pascal
Hopper
GPU Name
GP108B
GH100
Generation
GeForce MX
(3xx)
Server Hopper
(Hxx)
Process Size
14 nm
5 nm
Transistors
1,800 million
80,000 million
Die Size
74 mm²
814 mm²
Foundry
Samsung
TSMC
Density
24.3M / mm²
98.3M / mm²
API Support
DirectX
12 (12_1)
—
OpenGL
4.6
—
Vulkan
1.4
—
OpenCL
3.0
3.0
CUDA
6.1
9.0
Shader Model
6.8
—
Physical
Slot Width
IGP
Dual-slot
Length
—
267 mm
10.5 inches
Height
—
111 mm
4.4 inches
Outputs
Portable Device Dependent
No outputs
Bus Interface
PCIe 3.0 x4
PCIe 5.0 x16
Other
Production
End-of-life
Active
Predecessor
—
Server Ada
Successor
—
Server Blackwell