| 规格 | NVIDIA Quadro RTX 8000 | NVIDIA A30 |
|---|
| 架构 | Turing (TU102, TSMC 12nm FFN, 18.6B 晶体管) | NVIDIA Ampere |
| 显存 | 48GB GDDR6 with ECC | 24 GB HBM2 |
| 显存带宽 | 672GB/s (GDDR6 14Gbps) | 933 GB/s |
| 显存位宽 | 384bit | — |
| 算力 | FP32 16.3 TFLOPS (Boost) / Tensor 130.5 TFLOPS / FP16 32.6 TFLOPS / INT8 206.1 TOPS / RTX-OPS 84T / FP64=FP32的1/32≈509GFLOPS | — |
| CUDA核心 | 4608 (72 SM) / Tensor Cores 576 (图灵二代) / RT Cores 72 (一代) | — |
| 功耗 | 总板功耗 295W / 图形功耗 260W (含 USB-C/VirtualLink 为 295W, PNY 口径) | — |
| 互联 | NVLink 100GB/s 双向 (TU102 双 x8 链路, 双卡拼 96GB, NVLink 售卖) / PCIe 3.0 x16 | PCIe Gen4: 64GB/s / Third-gen NVLINK: 200GB/s |
| 发布年 | 2018 (2018-08-13 SIGGRAPH 温哥华发布[媒体多记08-14], Q4 2018 上市, 预计市场价 $10,000) | — |
| 形态 | Dual-slot 全高, 4.4"H x 10.5"L, Active 主动散热, 1x 8-pin 外接供电 | Dual-slot, full-height, full-length (FHFL) |
| 显示输出 | 4x DisplayPort 1.4 + VirtualLink (USB Type-C) | — |
| 编解码 | 1 Encode / 1 Decode | — |
| VR | Yes (VR Ready, 业界首个 VirtualLink 接口) | — |
| API | DirectX 12.0 (FL 12_1) / OpenGL 4.6 / Vulkan 1.1 / CUDA / OpenCL / DirectCompute | — |
| FP32算力 | — | 10.3 teraFLOPS |
| FP64算力 | — | 5.2 teraFLOPS |
| TF32算力 | — | 82 teraFLOPS | 165 teraFLOPS |
| FP16算力 | — | 165 teraFLOPS | 330 teraFLOPS |
| INT8算力 | — | 330 TOPS | 661 TOPS |
| 功耗TDP | — | 165 W |
| MIG | — | 4 GPU instances @ 6GB each |