MetaX · Accelerator Card
N100
MetaX N100 is an intelligent inference GPU for diverse intelligent applications. Featuring an innovatively architected GPGPU, it delivers powerful AI computing power and exceptional video encoding/decoding capabilities. It can be widely used in smart cities, intelligent transportation, smart education, and intelligent video processing.
Key Highlights
- Innovative computing architecture optimized for inference scenarios
- Equipped with 16GB GPU Memory
- Single-card support for up to 128 channels of video encoding capability
- Half-Height, Half-Length (HHHL), single-slot PCIe card with a Maximum Board Power of 70W
Technical Specifications
| GPU Memory | 16GB 高带宽显存 / 16GB GPU Memory |
|---|---|
| Video Codec | 单卡最高128路视频编码 / up to 128 channels video encoding per card |
| 精度算力（FP16/FP8/INT8, TFLOPS/TOPS）/ Precision Compute: | |
| Interconnect | PCIe（代数官网未公开 / PCIe generation not disclosed） |
| Typical Board Power | 最大70W / Max 70W |
| Form Factor | 半高半长单槽位PCIe板卡 / Half-Height Half-Length single-slot PCIe card |
Typical Use Cases
Smart CityIntelligent TransportationShort VideoCloud Computing
img1: main; alt=官网产品页主视觉(banner); 官方图右下角标注"部分图片由大模型生成"，为含绿色科技背景的产品渲染主图。; 精度算力(FP16/FP8/INT8 TFLOPS/TOPS)、显存带宽、PCIe代数官网未公开；无公开硬件Datasheet PDF。
