
NVIDIA IGX Thor™プラットフォームは、産業グレードのハードウェア、エンタープライズ向けソフトウェア、そして機能安全性を備え、物理AIエージェント向けのリアルタイムセンサ処理とAI推論を実現します。
| 製品名 | NVIDIA IGX T5000 Module |
| JANコード | なし |
| 価格 | オープンプライス |
| 同梱物 | なし |
| 製品名 | NVIDIA IGX T7000 ボードキット |
| JANコード | なし |
| 価格 | オープンプライス |
| 同梱物 | なし |
| 項目 | NVIDIA IGX T5000 | NVIDIA IGX T7000 | |
|---|---|---|---|
| dGPU Option | - | With NVIDIA RTX Pro 6000 Blackwell Max-Q Workstation Edition |
With NVIDIA RTX Pro Blackwell 5000 |
| AI Performance | 2,070TFLOPS(FP4-Sparse) | Up to 5,581TFLOPS(FP4-Sparse) | Up to 4,293TFLOPS(FP4-Sparse) |
| iGPU | 2,560core NVIDIA Blackwell architecture GPU with 96 fifthgeneration Tensor Cores Multi-Instance GPU with 10 TPCs |
2,560core NVIDIA Blackwell architecture GPU with 96 fifthgeneration Tensor Cores Multi-Instance GPU with 10 TPCs |
2,560core NVIDIA Blackwell architecture GPU with 96 fifthgeneration Tensor Cores Multi-Instance GPU with 10 TPCs |
| iGPU Max Frequency |
1.57GHz | 1.57GHz | 1.57GHz |
| dGPU | - | 24,064core Blackwell architecture GPU with fifth-generation Tensor Cores |
14,080core Blackwell architecture GPU with fifth-generation Tensor Cores |
| CPU | 14core Arm Neoverse-V3AE 64bit CPU 64KB I-cache 64KB dCache 1MB L2 cache per core 16MB shared system L3 cache |
14core Arm Neoverse-V3AE 64bit CPU 64KB I-cache 64KB dCache 1MB L2 cache per core 16MB shared system L3 cache |
14core Arm Neoverse-V3AE 64bit CPU 64KB I-cache 64KB dCache 1MB L2 cache per core 16MB shared system L3 cache |
| CPU Max Frequency |
2.6GHz | 2.6GHz | 2.6GHz |
| Vision Accelerator |
1xPVA v3 | 1xPVA v3 | 1xPVA v3 |
| Memory | 128GB 256bit LPDDR5X 273GB/s |
128GB 256bit LPDDR5X | 273 GB/s 96GB dGPU memory | 1,792GB/s |
128GB 256bit LPDDR5X | 273GB/s 48GB dGPU memory | 1,344GB/s |
| Storage | Supports NVMe through PCIe Supports SSD through USB 3.2 |
4xSATA connectorsM.2 key M connector (PCIe Gen5 x2) |
4xSATA connectorsM.2 key M connector(PCIe Gen5x2) |
| Video Encode | 2xNVEncode | 2xNVEncode(iGPU) 4xNVEncode(dGPU) |
2xNVEncode(iGPU) 3xNVEncode(dGPU) |
| Video Decode | 2xNVDecode | 2xNVDecode(iGPU) 4xNVDecode(dGPU) |
2xNVDecode(iGPU) 3xNVDecode(dGPU) |
| PCIe | Up to 8lanes:Gen5 Root port only:C1(x1)and C3(x2) Root point or endpoint:C2(x1) C4(x8) and C5(x4) |
2xPCIe Gen5(x8、x16) | 2xPCIe Gen5(x8、x16) |
| USB | xHCI host controller with integrated PHY(up to) 3xUSB 3.2 4xUSB 2.0 |
1xUSB 3.2 TypeC 4xUSB 3.2 TypeA |
1xUSB 3.2 TypeC 4xUSB 3.2 TypeA |
| Networking | 4x25GbE | 2xRJ45(1GbE each) 2x QSFP28(200GbE each) |
2xRJ45(1GbE each) 2xQSFP28(200GbE each) |
| Integrated ConnectX |
No | Yes | Yes |
| Display | 1xshared HDMI 2.1 1xVESA DisplayPort 1.4a: HBR2、MST |
1xVESA DisplayPort 1.4a | 1xVESA DisplayPort 1.4a |
| Other I/O | 2x13pin CAN header 2x 6pin automation header 2x5pin header JTAG connector 1x4pin fan connector: 12V、 PWM、and tach 2x5pin audio panel header 2pin RTC backup battery connector |
2xUSB header for optional connection via cable 4xCOM Ports 1x LPT 1xTPM 1xCAN 1xGPIO Audio Line-out Mic In |
2xUSB header for optional connection via cable 4xCOM Ports 1xLPT 1xTPM 1xCAN 1xGPIO Audio Line-out Mic In |
| BMC | - | Yes | Yes |
| Safety Support | Functional Safety Island on SoC | Functional Safety Island on SoC Safety MCU on the carrier board |
Functional Safety Island on SoC Safety MCU on the carrier board |
| NVDIA AI Enterprise Support |
Yes | Yes | Yes |
| Power | 40W-130W | 40W-130W TMP Up to 300 W for dGPU |
40W-130W TMP Up to 300 W for dGPU |
| Mechanical | 100mmx87mm 699pin B2B connector Integrated thermal transfer plate(TTP)with heat pipe |
243.84mmx198.98mmx31.05mm | 243.84mmx198.98mmx31.05mm |
![]() |
![]() |