Computing Instance
Last updated:2026-02-26 17:05:57
GPU Computing instances provide powerful computing capabilities to help you process a large number of concurrent computing tasks in real time. They are suitable for general computing scenarios such as deep learning and scientific computing. They provide a fast, stable, and elastic computing service and can be managed just like CVM instances.
Note:
If your GPU instance is to be used for 3D rendering tasks, we recommend you use a rendering instance configured with a vDWs/vWs license and installed with a GRID driver. It eliminates the need to manually configure the basic environment for GPU-based graphics and image processing.
Overview
GPU Computing instances are available in the following types:
Availability | Resource Type | GPU Type | Available Regions |
Featured | NVIDIA A10 | Guangzhou, Shanghai, Nanjing, and Beijing | |
| NVIDIA A100 | Guangzhou, Shanghai, Nanjing, and Beijing | |
| NVIDIA V100 | Guangzhou, Shanghai, Nanjing, Beijing, Chengdu, Chongqing, Singapore, Bangkok, Seoul, Tokyo, Frankfurt, and Silicon Valley | |
| NVIDIA T4 | Guangzhou, Shanghai, Nanjing, Beijing, Chengdu, Chongqing, Hong Kong (China), Singapore, Bangkok, Jakarta, Seoul, Tokyo, Frankfurt, Silicon Valley, Virginia, and Sao Paulo | |
| NVIDIA T4 | Shanghai and Nanjing | |
Invitation for testing | NVIDIA GPU | Beijing, Shanghai, Nanjing, Guangzhou, Singapore, and Frankfurt | |
| NVIDIA GPU | Guangzhou, Shanghai, Nanjing, Beijing, and Shanghai Self-driving Cloud | |
| NVIDIA GPU | Hong Kong (China), Singapore, Frankfurt, and Tokyo | |
Available | NVIDIA T4 | Guangzhou, Shanghai, Beijing, Nanjing, Chengdu, and Chongqing | |
| NVIDIA V100 | Guangzhou, Shanghai, Nanjing, Beijing, Chengdu, Chongqing, Singapore, Frankfurt, and Silicon Valley | |
| NVIDIA P40 | Guangzhou, Shanghai, Beijing, Chengdu, Chongqing, Hong Kong (China), and Silicon Valley | |
| NVIDIA P4 | GN6: Chengdu GN6S: Guangzhou, Shanghai, and Beijing | |
Suggestions on Computing Instance Model Selection
Tencent Cloud provides NVIDIA GPU instances to meet business needs in different scenarios. Refer to the following tables to select an NVIDIA GPU instance as needed.
The table below lists recommended GPU Computing instance models. A tick (✓) indicates that the model supports the corresponding feature. A pentagram (★) indicates that the model is recommended.
Feature/Instance | PNV4 | GT4 | GN10Xp | GN7 | GN7vi | GI3X | GN10X | GN8 | GN6/GN6S |
Graphics and image processing | ✓ | - | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ |
Video encoding and decoding | ✓ | - | ✓ | ★ | ★ | ★ | ✓ | ✓ | ✓ |
Deep learning training | ✓ | ★ | ★ | ✓ | ✓ | ✓ | ★ | ★ | ✓ |
Deep learning inference | ★ | ✓ | ★ | ★ | ★ | ★ | ★ | ✓ | ✓ |
Scientific computing | - | ★ | ★ | - | - | - | ★ | - | - |
Note:
These recommendations are for reference only. Select an appropriate instance model based on your needs.
To use NVIDIA GPU instances for general computing tasks, you need to install the Tesla driver and CUDA toolkit. For more information, see Installing NVIDIA Driver and Installing CUDA Driver.
To use NVIDIA GPU instances for 3D rendering tasks such as high-performance graphics processing and video encoding and decoding, you need to install a GRID driver and configure a license server. For installation methods, see Installing NVIDIA GRID Driver.
Instance Specification
Computing PNV4
Computing PNV4 supports not only general GPU computing tasks such as deep learning, but also graphics and image processing tasks such as 3D rendering and video encoding and decoding.
Use cases
GN6 and GN6S are cost-effective and applicable to the following scenarios:
Deep learning inference and small-scale training scenarios, such as:
AI inference for mass deployment
Small-scale deep learning training
Graphic and image processing scenarios, such as:
Graphic and image processing
Video encoding and decoding
Graph database
Hardware specification
GPU: NVIDIA® A10 (FP32 31.2 TFLOPS, TF32 62.5 TFLOPS, FP16 125 TFLOPS, INT8 250 TOPS).
CPU: AMD EPYC™ Milan CPU 2.55 GHz, with a Max Boost frequency of 3.5 GHz.
Memory: Collocation with 8-channel DDR4 memory.
Storage: Select the appropriate CBS cloud disk type. To expand the cloud disk capacity, create and mount an elastic cloud disk.
Network: Network optimization is enabled by default. The network performance of an instance depends on its specification. You can purchase public network bandwidth as needed.
Specification | GPU | GPU Video Memory | vCPU | Memory (GiB) | Private Network Bandwidth (Gbps) | Packets In/Out(PPS) | Number of Queues |
PNV4.7XLARGE116 | NVIDIA A10 * 1 | 24GB * 1 | 28 | 116 | 13 | 2.3 million | 28 |
PNV4.14XLARGE232 | NVIDIA A10 * 2 | 24GB * 2 | 56 | 232 | 25 | 4.7 million | 48 |
PNV4.28XLARGE466 | NVIDIA A10 * 4 | 24GB * 4 | 112 | 466 | 50 | 9.5 million | 48 |
PNV4.56XLARGE932 | NVIDIA A10 * 8 | 24GB * 8 | 224 | 932 | 100 | 19 million | 48 |
Computing GT4
Computing GT4 instances are suitable for general GPU computing tasks such as deep learning and scientific computing.
Use cases
GT4 features powerful double-precision floating point computing capabilities. It is suitable for large-scale deep learning training and inference as well as scientific computing scenarios, such as:
Deep learning
High-performance database
Computational fluid dynamics
Computational finance
Seismic analysis
Molecular modeling
Genomics and others
Hardware specification
GPU: NVIDIA® A100 NVLink 40GB (FP64 9.7 TFLOPS, FP32 19.5 TFLOPS, 600GB/s NVLink).
CPU: 2.6GHz AMD EPYC™ ROME processor with a max turbo frequency of 3.3GHz.
Memory: Collocation with 8-channel DDR4 memory.
Storage: Select the appropriate CBS cloud disk type. To expand the cloud disk capacity, create and mount an elastic cloud disk.
Network: Private network bandwidth of up to 50 Gbps is supported, with strong packet sending/receiving capabilities. The network performance of an instance depends on its specification. You can purchase public network bandwidth as needed.
Specification | GPU | GPU Video Memory | vCPU | Memory (GiB) | Private Network Bandwidth (Gbps) | Packets In/Out(PPS) | Number of Queues |
GT4.4XLARGE96 | NVIDIA A100 * 1 | 40GB * 1 | 16 | 96 | 5 | 1.2 million | 4 |
GT4.8XLARGE192 | NVIDIA A100 * 2 | 40GB * 2 | 32 | 192 | 10 | 2.35 million | 8 |
GT4.20XLARGE474 | NVIDIA A100 * 4 | 40GB * 4 | 82 | 474 | 25 | 6 million | 16 |
GT4.41XLARGE948 | NVIDIA A100 * 8 | 40GB * 8 | 164 | 948 | 50 | 12 million | 32 |
Note:
GPU driver: Drivers of NVIDIA Tesla 450 or later are required for NVIDIA A100 GPUs. For more information on driver versions, see NVIDIA Driver Documentation.
Computing GN10Xp
Computing GN10Xp instances support not only general GPU computing tasks such as deep learning and scientific computing, but also graphics and image processing tasks such as 3D rendering and video encoding and decoding.
Use cases
GN10Xp features powerful double-precision floating point computing capabilities. It is suitable for the following scenarios:
Large-scale deep learning training and inference as well as scientific computing scenarios, such as:
Deep learning
High-performance database
Computational fluid dynamics
Computational finance
Seismic analysis
Molecular modeling
Genomics and others
Graphic and image processing scenarios, such as:
Graphic and image processing
Video encoding and decoding
Graph database
Hardware specification
CPU: Intel® Xeon® Platinum 8255C CPU, with a clock rate of 2.5 GHz.
GPU: NVIDIA® Tesla® V100 NVLink 32GB, providing 15.7 TFLOPS of single-precision floating point performance, 7.8 TFLOPS of double-precision floating point performance, 125 TFLOPS of deep learning accelerator performance with Tensor cores, and 300 GB/s NVLink.
Memory: DDR4 with a memory speed of up to 2666 MT/s.
Storage: Select the appropriate CBS cloud disk type. To expand the cloud disk capacity, create and mount an elastic cloud disk.
Network: Network optimization is enabled by default. The network performance of an instance depends on its specification. You can purchase public network bandwidth as needed.
Specification | GPU | GPU Video Memory | vCPU | Memory (GiB) | Private Network Bandwidth (Gbps) | Packets In/Out(PPS) | Number of Queues |
GN10Xp.2XLARGE40 | NVIDIA V100 * 1 | 32GB * 1 | 10 | 40 | 3 | 0.8 million | 2 |
GN10Xp.5XLARGE80 | NVIDIA V100 * 2 | 32GB * 2 | 20 | 80 | 6 | 1.5 million | 5 |
GN10Xp.10XLARGE160 | NVIDIA V100 * 4 | 32GB * 4 | 40 | 160 | 12 | 2.5 million | 10 |
GN10Xp.20XLARGE320 | NVIDIA V100 * 8 | 32GB * 8 | 80 | 320 | 24 | 4.9 million | 16 |
Computing GN7
NVIDIA GPU instance GN7 supports not only general GPU computing tasks such as deep learning, but also graphic and image processing tasks such as 3D rendering and video encoding and decoding.
Use cases
GN6 and GN6S are cost-effective and applicable to the following scenarios:
Deep learning inference and small-scale training scenarios, such as:
AI inference for mass deployment
Small-scale deep learning training
Graphic and image processing scenarios, such as:
Graphic and image processing
Video encoding and decoding
Graph database
Hardware specification
CPU: Intel® Xeon® Platinum 8255C CPU, with a clock rate of 2.5 GHz.
GPU: NVIDIA® Tesla® T4, providing 8.1 TFLOPS of single-precision floating point performance, 130 TOPS for INT8, and 260 TOPS for INT4.
Memory: DDR4 with a memory speed of up to 2666 MT/s.
Storage: Select the appropriate CBS cloud disk type. To expand the cloud disk capacity, create and mount an elastic cloud disk.
Network: Network optimization is enabled by default. The network performance of an instance depends on its specification. You can purchase public network bandwidth as needed.
Specification | GPU | GPU Video Memory | vCPU | Memory (GiB) | Private Network Bandwidth (Gbps) | Packets In/Out(PPS) | Number of Queues |
GN7.2XLARGE32 | NVIDIA T4 * 1 | 16GB * 1 | 8 | 32 | 3 | 0.6 million | 8 |
GN7.5XLARGE80 | NVIDIA T4 * 1 | 16GB * 1 | 20 | 80 | 7 | 1.4 million | 10 |
GN7.8XLARGE128 | NVIDIA T4 * 1 | 16GB * 1 | 32 | 128 | 10 | 2.4 million | 16 |
GN7.10XLARGE160 | NVIDIA T4 * 2 | 16GB * 2 | 40 | 160 | 13 | 2.8 million | 20 |
GN7.20XLARGE320 | NVIDIA T4 * 4 | 16GB * 4 | 80 | 320 | 25 | 5.6 million | 32 |
Video enhancement GN7vi
NVIDIA GN7vi instances
are GN7 instances configured with Tencent's proprietary MPS technology and integrated with AI. They include the TSC encoding and decoding engine and image quality enhancement toolkit and are suitable for VOD and live streaming scenarios. This type of instance allows you to leverage Tencent Cloud's proprietary TSC encoding and decoding as well as AI image quality enhancement features.Hardware specification
CPU: Intel® Xeon® Platinum 8255C CPU, with a clock rate of 2.5 GHz.
GPU: NVIDIA® Tesla® T4, providing 8.1 TFLOPS of single-precision floating point performance, 130 TOPS for INT8, and 260 TOPS for INT4.
Memory: DDR4 with a memory speed of up to 2666 MT/s.
Storage: Select the appropriate CBS cloud disk type. To expand the cloud disk capacity, create and mount an elastic cloud disk.
Network: Network optimization is enabled by default. The network performance of an instance depends on its specification. You can purchase public network bandwidth as needed.
Specification | GPU | GPU Video Memory | vCPU | Memory (GiB) | Private Network Bandwidth (Gbps) | Packets In/Out(PPS) | Number of Queues |
GN7vi.5XLARGE80 | NVIDIA T4 * 1 | 16GB * 1 | 20 | 80 | 6 | 1.4 million | 20 |
GN7vi.10XLARGE160 | NVIDIA T4 * 2 | 16GB * 2 | 40 | 160 | 13 | 2.8 million | 32 |
GN7vi.20XLARGE320 | NVIDIA T4 * 4 | 16GB * 4 | 80 | 320 | 25 | 5.6 million | 32 |
Computing PNV5b (Beta)
Computing PNV5b
uses a new architecture GPU card with 48GB GDDR6 memory capacity, supporting FP32, FP16, BF16, FP8, and INT8 computation formats. It is paired with AMD EPYC™ Genoa processors, suitable for deep learning inference, advertising recommendation, and other scenarios, as well as graph and image processing (3D rendering, video codec) scenarios.Note:
This instance is currently in the beta testing stage with allowlist access. Contact your pre-sales manager to enable purchase permission for the instance.
Scenarios
Inference scenarios for deep learning and ad recommendation scenarios, such as:
LLM inference
Advertising recommendation
AIGC（image and video generation）
Graphics and image processing scenario. For example:
Graphics and image processing
Video Encoding and Decoding
Graphic databases
Hardware Specifications
CPU：AMD EPYC™ Turin-D CPU 2.25 GHz, with a Max Boost frequency of 3.4 GHz.
Memory: Collocation with 12-channel DDR5 memory.
Storage: Select the appropriate CBS cloud disk type. To expand the cloud disk capacity, create and mount an elastic cloud disk.
Network: Network optimization is enabled by default. The network performance of an instance depends on its specification. You can purchase public network bandwidth as needed.
Specification | GPU | GPU Video Memory | vCPU | Memory (GiB) | Private Network Bandwidth (Gbps) | Packets In/Out(PPS) | Number of Queues |
PNV5b.8XLARGE96 | NVIDIA GPU * 1 | 48GB * 1 | 32 | 96 | 13 | 5.6 million | 32 |
PNV5b.12XLARGE192 | NVIDIA GPU * 1 | 48GB * 1 | 48 | 192 | 13 | 5.6 million | 48 |
PNV5b.16XLARGE192 | NVIDIA GPU * 2 | 48GB * 2 | 64 | 192 | 25 | 11.2 million | 48 |
PNV5b.24XLARGE384 | NVIDIA GPU * 2 | 48GB * 2 | 96 | 384 | 25 | 11.2 million | 48 |
PNV5b.32XLARGE384 | NVIDIA GPU * 4 | 48GB * 4 | 128 | 384 | 50 | 22.5 million | 48 |
PNV5b.48XLARGE768 | NVIDIA GPU * 4 | 48GB * 4 | 192 | 768 | 50 | 22.5 million | 48 |
PNV5b.64XLARGE768 | NVIDIA GPU * 8 | 48GB * 8 | 256 | 1536 | 100 | 45 million | 48 |
PNV5b.96XLARGE1536 | NVIDIA GPU * 8 | 48GB * 8 | 384 | 1536 | 100 | 45 million | 48 |
Computing PNV6 (Beta)
Computing PNV6 is suitable for deep learning inference and small-scale training scenarios.
Note:
This instance is currently in the beta testing stage with allowlist access. Contact your pre-sales manager to enable purchase permission for the instance.
Scenarios
High cost-effectiveness, suitable for the following scenarios:
Reasoning scenarios and small-scale training scenarios for deep learning. For example:
Large language model inference
Ad recommendations
Autonomous driving
Computer vision
Hardware Specifications
CPU: AMD EPYC™ Genoa processor with a boost clock of 3.7GHz.
Memory: Collocation with 12-channel DDR5 memory.
Storage: Select the appropriate CBS cloud disk type. To expand the cloud disk capacity, create and mount an elastic cloud disk.
Network: Network optimization is enabled by default. The network performance of an instance depends on its specification. You can purchase public network bandwidth as needed.
Specification | GPU | GPU Video Memory | vCPU | Memory (GiB) | Private Network Bandwidth (Gbps) | Packets In/Out(PPS) | Number of Queues |
PNV6.4XLARGE160 | NVIDIA GPU * 1 | 96GB * 1 | 16 | 160 | 8 | 1.8 million | 16 |
PNV6.8XLARGE320 | NVIDIA GPU * 2 | 96GB * 2 | 32 | 320 | 13 | 3.7 million | 32 |
PNV6.16XLARGE640 | NVIDIA GPU * 4 | 96GB * 4 | 64 | 640 | 25 | 7.5 million | 48 |
PNV6.32XLARGE1280 | NVIDIA GPU * 8 | 96GB * 8 | 128 | 1280 | 50 | 15 million | 48 |
PNV6.96XLARGE2304 | NVIDIA GPU * 8 | 96GB * 8 | 384 | 2304 | 100 | 45 million | 48 |
Computing PNV6s (Beta)
Computing PNV6s is suitable for deep learning inference and small-scale training scenarios.
Note:
This instance is currently in the beta testing stage with allowlist access. Contact your pre-sales manager to enable purchase permission for the instance.
Scenarios
High cost-effectiveness, suitable for the following scenarios:
Reasoning scenarios and small-scale training scenarios for deep learning. For example:
Large language model inference
Ad recommendations
Autonomous driving
Computer vision
Hardware Specifications
CPU: AMD EPYC™ Genoa processor with a boost clock of 3.7GHz.
Memory: Collocation with 12-channel DDR5 memory.
Storage: Select the appropriate CBS cloud disk type. To expand the cloud disk capacity, create and mount an elastic cloud disk.
Network: Network optimization is enabled by default. The network performance of an instance depends on its specification. You can purchase public network bandwidth as needed.
Specification | GPU | GPU Video Memory | vCPU | Memory (GiB) | Private Network Bandwidth (Gbps) | Packets In/Out(PPS) | Number of Queues |
PNV6s.4XLARGE160 | NVIDIA GPU * 1 | 141GB * 1 | 16 | 160 | 8 | 1.8 million | 16 |
PNV6s.8XLARGE320 | NVIDIA GPU * 2 | 141GB * 2 | 32 | 320 | 13 | 3.7 million | 32 |
PNV6s.16XLARGE640 | NVIDIA GPU * 4 | 141GB * 4 | 64 | 640 | 25 | 7.5 million | 48 |
PNV6s.32XLARGE1280 | NVIDIA GPU * 8 | 141GB * 8 | 128 | 1280 | 50 | 15 million | 48 |
PNV6s.96XLARGE2304 | NVIDIA GPU * 8 | 141GB * 8 | 384 | 2304 | 100 | 45 million | 48 |
Interference GI3X
NVIDIA GI3X supports not only general GPU computing tasks such as deep learning, but also graphics and image processing tasks such as 3D rendering and video encoding and decoding.
Use cases
GI3X is cost-effective and applicable to the following scenarios:
Deep learning inference and small-scale training scenarios, such as:
AI inference for mass deployment
Small-scale deep learning training
Graphic and image processing scenarios, such as:
Graphic and image processing
Video encoding and decoding
Graph database
Hardware specification
CPU: AMD EPYC™ ROME CPU 2.6 GHz, with a Max Boost frequency of 3.3 GHz.
GPU: NVIDIA® Tesla® T4, providing 8.1 TFLOPS of single-precision floating point performance, 130 TOPS for INT8, and 260 TOPS for INT4.
Memory: Latest eight-channel DDR4 with stable computing performance.
Storage: Select the appropriate CBS cloud disk type. To expand the cloud disk capacity, create and mount an elastic cloud disk.
Network: Network optimization is enabled by default. The network performance of an instance depends on its specification. You can purchase public network bandwidth as needed.
GI3X instances are available in the following configurations:
Specification | GPU | GPU Video Memory | vCPU | Memory (GiB) | Private Network Bandwidth (Gbps) | Packets In/Out(PPS) | Number of Queues |
GI3X.8XLARGE64 | NVIDIA T4 * 1 | 16GB * 1 | 32 | 64 | 5 | 1.4 million | 8 |
GI3X.22XLARGE226 | NVIDIA T4 * 2 | 16GB * 2 | 90 | 226 | 13 | 3.75 million | 16 |
GI3X.45XLARGE452 | NVIDIA T4 * 4 | 16GB * 4 | 180 | 452 | 25 | 7.5 million | 32 |
Computing GN10X
Computing GN10X supports not only general GPU computing tasks such as deep learning and scientific computing, but also graphics and image processing tasks such as 3D rendering and video encoding and decoding.
Use cases
GN10X features powerful double-precision floating point computing capabilities. It is suitable for the following scenarios:
Large-scale deep learning training and inference as well as scientific computing scenarios, such as:
Deep learning
High-performance database
Computational fluid dynamics
Computational finance
Seismic analysis
Molecular modeling
Genomics and others
Graphic and image processing scenarios, such as:
Graphic and image processing
Video encoding and decoding
Graph database
Hardware specification
CPU: GN10X is configured with an Intel® Xeon® Gold 6133 CPU, with a clock rate of 2.5 GHz.
GPU: NVIDIA® Tesla® V100 NVLink 32GB, providing 15.7 TFLOPS of single-precision floating point performance, 7.8 TFLOPS of double-precision floating point performance, 125 TFLOPS of deep learning accelerator performance with Tensor cores, and 300 GB/s NVLink.
Memory: DDR4 with a memory speed of up to 2666 MT/s.
Storage: Select the appropriate CBS cloud disk type. To expand the cloud disk capacity, create and mount an elastic cloud disk.
Network: Network optimization is enabled by default. The network performance of an instance depends on its specification. You can purchase public network bandwidth as needed.
GN10X instances are available in the following configurations:
Specification | GPU | GPU Video Memory | vCPU | Memory (GiB) | Private Network Bandwidth (Gbps) | Packets In/Out(PPS) | Number of Queues |
GN10X.2XLARGE40 | NVIDIA V100 * 1 | 32GB * | 8 | 40 | 3 | 0.8 million | 2 |
GN10X.4XLARGE80 | NVIDIA V100 * 2 | 32GB * 2 | 18 | 80 | 7 | 1.5 million | 4 |
GN10X.9XLARGE160 | NVIDIA V100 * 4 | 32GB * 4 | 36 | 160 | 13 | 2.5 million | 9 |
GN10X.18XLARGE320 | NVIDIA V100 * 8 | 32GB * 8 | 72 | 320 | 25 | 4.9 million | 16 |
Computing GN8
NVIDIA GPU instance GN8 supports not only general GPU computing tasks such as deep learning, but also graphic and image processing tasks such as 3D rendering and video encoding and decoding.
Use cases
GN8 is applicable to the following scenarios:
Deep learning training and inference scenarios, such as:
AI inference with high throughput
Deep learning
Graphic and image processing scenarios, such as:
Graphic and image processing
Video encoding and decoding
Graph database
Hardware specification
CPU: Intel® Xeon® E5-2680 v4 CPU, with a clock rate of 2.4 GHz.
GPU: NVIDIA® Tesla® P40, providing 12 TFLOPS of single-precision floating point performance and 47 TOPS for INT8.
Memory: DDR4 with a memory speed of up to 2666 MT/s.
Storage: Select the appropriate CBS cloud disk type. To expand the cloud disk capacity, create and mount an elastic cloud disk.
Network: Network optimization is enabled by default. The network performance of an instance depends on its specification. You can purchase public network bandwidth as needed.
GN8 instances are available in the following configurations:
Specification | GPU | GPU Video Memory | vCPU | Memory (GiB) | Private Network Bandwidth (Gbps) | Packets In/Out(PPS) | Number of Queues |
GN8.LARGE56 | NVIDIA P40 * 1 | 24GB * 1 | 6 | 56 | 1.5 | 0.45 million | 8 |
GN8.3XLARGE112 | NVIDIA P40 * 2 | 24GB * 2 | 14 | 112 | 2.5 | 0.5 million | 8 |
GN8.7XLARGE224 | NVIDIA P40 * 4 | 24GB * 4 | 28 | 224 | 5 | 0.7 million | 14 |
GN8.14XLARGE448 | NVIDIA P40 * 8 | 24GB * 8 | 56 | 448 | 10 | 0.7 million | 28 |
Computing GN6 and GN6S
NVIDIA GPU instances GN6 and GN6S support not only general GPU computing tasks such as deep learning, but also graphic and image processing tasks such as 3D rendering and video encoding and decoding.
Use cases
GN6 and GN6S are cost-effective and applicable to the following scenarios:
Deep learning inference and small-scale training scenarios, such as:
AI inference for mass deployment
Small-scale deep learning training
Graphic and image processing scenarios, such as:
Graphic and image processing
Video encoding and decoding
Graph database
Hardware specification
CPU: GN6 is configured with an Intel® Xeon® E5-2680 v4 CPU, with a clock rate of 2.4 GHz. GN6S is configured with an Intel® Xeon® Silver 4110 CPU, with a clock rate of 2.1 GHz.
GPU: NVIDIA® Tesla® P4, providing 5.5 TFLOPS of single-precision floating point performance and 22 TOPS for INT8.
Memory: DDR4 with a memory speed of up to 2666 MT/s.
Storage: Select the appropriate CBS cloud disk type. To expand the cloud disk capacity, create and mount an elastic cloud disk.
Network: Network optimization is enabled by default. The network performance of an instance depends on its specification. You can purchase public network bandwidth as needed.
GN6 and GN6S instances are available in the following configurations:
Specification | GPU | GPU Video Memory | vCPU | Memory (GiB) | Private Network Bandwidth (Gbps) | Packets In/Out(PPS) | Number of Queues |
GN6.7XLARGE48 | NVIDIA P4 * 1 | 8GB * 1 | 28 | 48 | 5 | 1.2 million | 14 |
GN6.14XLARGE96 | NVIDIA P4 * 2 | 8GB * 2 | 56 | 96 | 10 | 1.2 million | 28 |
GN6S.LARGE20 | NVIDIA P4 * 1 | 8GB * 1 | 4 | 20 | 5 | 0.5 million | 8 |
GN6S.2XLARGE40 | NVIDIA P4 * 2 | 8GB * 2 | 8 | 40 | 9 | 0.8 million | 8 |
Was this page helpful?
You can also Contact Sales or Submit a Ticket for help.
Yes
No
Feedback