Für alle Technik-Begeisterten nachfolgend unser KI-Server für M4.0-Digitalisierungsprojekte
CPU: 2x AMD EPYC 7413
- 24 Cores
- 48 Threads
- Boost Clock: Up to 3.6 GHz
- L3 Cache: 128 MB
- Architecture: Zen 3
- TDP: 200 W
GPU: 2x Nvidia A40
- 48 GB GDDR6 ECC
- CUDA Cores: 10,752
- RT Cores: 84
- Tensor Cores: 336
- Peak FP32 TFLOPS (non-Tensor): 37.4
- Peak FP16 Tensor TFLOPS with FP16 Accumulate: 149.7
- Peak TF32 Tensor TFLOPS: 74.8
- RT Core performance TFLOPS: 73.1
- Peak BF16 Tensor TFLOPS with FP32 Accumulate: 149.7
- Peak INT8 Tensor TOPS: 299.3
- Peak INT4 Tensor TOPS: 598.7
- Max power consumption: 300 W
RAM: 512 GB 3200 MT/s CL22 Registered ECC