| IGX T5000IGX Thor system-on-module (P/N 900-23834-0080-000) for custom carrier boards with optional functional safety; a separate SKU from Jetson T5000 (P/N 900-13834-0080-001) but form-factor and pin-compatible with it. 2070 FP4 TFLOPS (sparse), 2560-core Blackwell GPU, 14-core Neoverse-V3AE, 128GB LPDDR5X, 4x 25GbE, 699-pin B2B, 40-130 W; no dGPU support (use IGX T7000). | Memory: 128 GB |
| Jetson AGX Orin 32GBAmpere SoM; up to 200 INT8 TOPS (sparse), 1792 CUDA + 56 Tensor cores, 8-core Cortex-A78AE, 32GB LPDDR5, 15–40W. | Max AI Performance (TOPS): 200 TOPSMemory: 32 GB |
| Jetson AGX Orin 64GBFlagship Ampere SoM; up to 275 INT8 TOPS (sparse), 2048 CUDA + 64 Tensor cores, 12-core Cortex-A78AE, 64GB LPDDR5 (204.8 GB/s), dual NVDLA, 15–60W. | Max AI Performance (TOPS): 275 TOPSMemory: 64 GB |
| Jetson AGX Orin IndustrialIndustrial-grade Ampere SoM; up to 248 INT8 TOPS, 2048 CUDA + 64 Tensor cores, 64GB LPDDR5, extended temp, 15–75W; pin-compatible with AGX Orin. | Max AI Performance (TOPS): 248 TOPSMemory: 64 GB |
| Jetson AGX Thor T5000Flagship Blackwell-generation SoM for physical AI/humanoid robotics; up to 2070 FP4 TFLOPS, 128GB LPDDR5X (273 GB/s), PCIe Gen5, 25GbE, dual NVDEC/NVENC, MIG-capable. | Max AI Performance (TOPS): 1,035 TOPSMemory: 128 GB |
| Jetson AGX Xavier 32GBVolta SoM; up to 32 INT8 TOPS, 512 CUDA + 64 Tensor cores, 8-core Carmel, 32GB LPDDR4x, 10–30W. | Max AI Performance (TOPS): 32 TOPSMemory: 32 GB |
| Jetson AGX Xavier 64GBVolta SoM; up to 32 INT8 TOPS, 512 CUDA + 64 Tensor cores, 8-core Carmel, 64GB LPDDR4x, dual NVDLA, 10–30W. | Max AI Performance (TOPS): 32 TOPSMemory: 64 GB |
| Jetson AGX Xavier IndustrialIndustrial Volta SoM; up to 30 INT8 TOPS, 512 CUDA + 64 Tensor cores, 8-core Carmel, 32GB LPDDR4x, extended temp, 20–40W. | Max AI Performance (TOPS): 30 TOPSMemory: 32 GB |
| Jetson NanoEntry Maxwell SoM; 472 GFLOPS FP16, 128 CUDA cores, 4-core Cortex-A57, 4GB LPDDR4 (25.6 GB/s), 5–10W; for entry edge AI/IoT. | Memory: 4 GB |
| Jetson Orin Nano 4GBEntry Ampere SoM; up to 34 INT8 TOPS (Super mode), 512 CUDA + 16 Tensor cores, 6-core Cortex-A78AE, 4GB LPDDR5, 7–25W. | Max AI Performance (TOPS): 20 TOPSMemory: 4 GB |
| Jetson Orin Nano 8GBEntry Ampere SoM; up to 67 INT8 TOPS (Super mode), 1024 CUDA + 32 Tensor cores, 6-core Cortex-A78AE, 8GB LPDDR5 (102 GB/s), 7–25W. | Max AI Performance (TOPS): 40 TOPSMemory: 8 GB |
| Jetson Orin NX 16GBCompact Ampere SoM; up to 157 INT8 TOPS (Super mode), 1024 CUDA + 32 Tensor cores, 8-core Cortex-A78AE, 16GB LPDDR5, 10–40W. | Max AI Performance (TOPS): 100 TOPSMemory: 16 GB |
| Jetson Orin NX 8GBCompact Ampere SoM; up to 117 INT8 TOPS (Super mode), 1024 CUDA cores, 6-core Cortex-A78AE, 8GB LPDDR5, 10–40W. | Max AI Performance (TOPS): 70 TOPSMemory: 8 GB |
| Jetson T4000Mid-tier Blackwell Thor SoM; up to 1200 FP4 TFLOPS, 64GB memory, 40–70W — over 4x AGX Orin AI compute with high energy efficiency. | Max AI Performance (TOPS): 600 TOPSMemory: 64 GB |
| Jetson TX2Pascal SoM; 1.33 TFLOPS FP16, 256 CUDA cores, dual-Denver + 4-core Cortex-A57, 8GB LPDDR4, 7.5–15W. | Memory: 8 GB |
| Jetson TX2 4GBPascal SoM; 256 CUDA cores, 6-core CPU, 4GB LPDDR4, 7.5–15W; cost-optimized TX2. | Memory: 4 GB |
| Jetson TX2 NXReduced-form-factor Pascal SoM (Nano/Xavier NX pin-compatible); 256 CUDA cores, 6-core CPU, 4GB LPDDR4, 7.5–15W. | Memory: 4 GB |
| Jetson TX2iIndustrial/rugged Pascal SoM; 256 CUDA cores, 6-core CPU, 8GB LPDDR4 ECC, extended temp/vibration, ~10–20W. | Memory: 8 GB |
| Jetson Xavier NX 16GBCompact Volta SoM; up to 21 INT8 TOPS, 384 CUDA + 48 Tensor cores, 6-core Carmel, 16GB LPDDR4x, 10–20W. | Max AI Performance (TOPS): 21 TOPSMemory: 16 GB |
| Jetson Xavier NX 8GBCompact Volta SoM; up to 21 INT8 TOPS, 384 CUDA + 48 Tensor cores, 6-core Carmel, 8GB LPDDR4x, 10–15W. | Max AI Performance (TOPS): 21 TOPSMemory: 8 GB |