Quadro T400E PCIe 4GB SSLP w/ATX bracket BULK NVIDIA Turing GPU architecture. NVIDIA Long-life SKU, Product Life Extended Until 2029. 384 NVIDIA® CUDA® Cores. 4 GB GDDR6 Memory. 80 GB/s Memory Bandwidth. Max. Power Consumption: 30 W. Graphics Bus: PCI-E 3.0 x16. Thermal Solution: Active. Display Connectors: mDP 1.4.
Quadro A1000 MXM 4GB Discrete mode Type A NVIDIA RTX A1000 with MXM 3.1 TYPE A form factor (82 x 70 mm). Up to 2048 CUDA cores , 16 RT cores and 64 Tensor cores, 6.66 TFLOPS. GDDR6 4GB memory, 128-bit, bandwidth 224 GB/s. Up to 4 x DisplayPort 1.4a outputs. Long life cycle, supports 5 years availability.
Quadro 3500 Ada MXM 12GB Discrete mode Type B+ NVIDIA® Quadro® 3500 Ada with MXM 3.1 TYPE B+ form factor (82 x 105 mm). Up to 5120 CUDA cores , 40 RT cores and 160 Tensor cores, 23.04 TFLOPS. GDDR6 12GB memory, 192-bit, bandwidth 432 GB/s. Discrete or MS-Hybrid mode supported. Memory Error Correction Code (ECC) supported. Encode Sessions Unlimite....
NVIDIA Jetson Orin Nano 8G Lite AI System_Super Fanless and ultra-compact design. Embedded with NVIDIA® Jetson Orin™ Nano up to 67 TOPS. Supports 1 x GbE, 2 x USB 3.2 Gen 1 (5 Gbit/s). Supports 1 x mPCIe, 1 x M.2 3052, 1 x M.2 2280. Supports Allxon 24/7 remote monitoring and OTA deployment. Supports Super mode with Jetpack 6.2 and above.
Quadro 2000 Ada MXM 8GB Discrete mode Type A NVIDIA Ada-Lovelace architecture Quadro® 2000A with MXM 3.1 TYPE A form factor (82 x 70 mm). Up to 3072 CUDA cores, 24 RT cores and 96 Tensor cores, 12.99 TFLOPS. GDDR6 8GB memory, 128-bit, bandwidth 256 GB/s. Discrete or MS-Hybrid mode supported. Memory Error Correction Code (ECC) supported. Encode Sessions...
ITA-560 NV Jetson AGX Orin_32G AI computing 110V Fanless box computer designed for AI inference. Embedded NVIDIA® Jetson AGX Orin™ platform. Compliant with EN 50155 OT1 and EN 50121-3-2 EMC standards. Rugged M12 connectors suitable for harsh, industrial environments. 1 x Mini PCIe, 1 x M.2 (M-key)for easy expansion. Bundled with Linux Ubuntu 20.04/22.04...
Tesla L4 24GB PCIe SSLP w/ATX BKT NVIDIA Ada-Lovelace GPU architecture. Universal Compute & Graphics GPU. 7680 NVIDIA® CUDA® Cores. 240 NVIDIA® Tensor Cores; 60 NVIDIA® RT Cores. 24GB with ECC memory. Up to 300 GB/s memory bandwidth. Max. power consumption: 72W. Graphics bus: PCIe 4.0 x16. PN：SKY-TESL-L4-24P.
MIC-733 32GB ITS traffic vertical application Compact fanless design. Embedded with NVIDIA® Jetson AGX Orin™. NEMA TS2 compliance. -34 to 74°C operating temperature support. 500ms power interruption backup (Based on NEMA TS2).
Tesla H100 NVL 94GB PCIe DSFH w/ATX BKT NVIDIA Hopper GPU architecture. Compute-optimized GPU. 14592 NVIDIA® CUDA® Cores. 456 NVIDIA® Tensor Cores. 94GB HBM2e memory with ECC. Up to 3.9TB/s memory bandwidth. Max. power consumption: 400W. Graphics bus: PCI-E 5.0 x16. Thermal solution: Passive.
ITA-560 NV Jetson AGX Orin_64G AI computing 24V Fanless box computer designed for AI inference. Embedded NVIDIA® Jetson AGX Orin™ platform. Compliant with EN 50155 OT1 and EN 50121-3-2 EMC standards. Rugged M12 connectors suitable for harsh, industrial environments. 1 x Mini PCIe, 1 x M.2 (M-key)for easy expansion. Bundled with Linux Ubuntu 20.04/22.04...
ITA-560 NV Jetson AGX Orin_64G AI computing 110V Fanless box computer designed for AI inference. Embedded NVIDIA® Jetson AGX Orin™ platform. Compliant with EN 50155 OT1 and EN 50121-3-2 EMC standards. Rugged M12 connectors suitable for harsh, industrial environments. 1 x Mini PCIe, 1 x M.2 (M-key)for easy expansion. Bundled with Linux Ubuntu 20.04/22.04...
ITA-560 NV Jetson AGX Orin_32G AI computing 24V Fanless box computer designed for AI inference. Embedded NVIDIA® Jetson AGX Orin™ platform. Compliant with EN 50155 OT1 and EN 50121-3-2 EMC standards. Rugged M12 connectors suitable for harsh, industrial environments. 1 x Mini PCIe, 1 x M.2 (M-key)for easy expansion. Bundled with Linux Ubuntu 20.04/22.04...
NVIDIA Jetson Orin NX 8G Lite AI System_Super Fanless and ultra-compact design. Embedded with NVIDIA® Jetson Orin™ NX up to 157 TOPS. Support 1 x GbE, 2 x USB3.2 Gen1 (5Gbit/s). Support 1 x mPCIe, 1 x M.2 3052, 1 x M.2 2280. Supports Allxon 24/7 remote monitoring and OTA deployment. Supports Super mode with Jetpack 6.2 and above.
RTX PRO 6000 Blackwell Server PCIe 96GB DSFH NVIDIA Blackwell GPU architecture. Single-Precision (FP32) Performance 117 TFLOPS. RT Core Performance 354.5 TFLOPS. 24,064 CUDA cores. 752 Tensor Cores ; 188 RT Cores. 96GB GDDR7 memory with ECC. 4.4” H x 10.5”L, FHFL Dual Slot. Max Power Consumption: Up to 600W (Configurable). 4 x Multi-instance GPU (MIG).
RTX PRO 6000 Blackwell PCIe 96GB DSXH NVIDIA Blackwell GPU architecture. AI Performance 4000 TOPS. Single-Precision (FP32) Performance 125 TFLOPS. 24,064 CUDA cores. 96GB GDDR7 memory with ECC. 5.4” H x 12”L, XHFL Dual Slot. Max Power Consumption: 600W. 4 x Multi-instance GPU (MIG). 4 x DisplayPort 2.1.
ITA-510 NV Jetson Orin NX_16G AI computing 24V Fanless system designed for AI inference. Embedded NVIDIA® Jetson Orin™ NX/ Orin™ Nano platform. Compliant with EN 50155 OT1 and EN 50121-3-2 EMC standards. Rugged M12 connectors suitable for harsh, industrial environments. 1 x Mini PCIe, 1 x M.2 (E-key),1 x M.2 (M-key) and 1 x M.2 (B-key) for easy...
Quadro A4500 MXM 16GB MS-Hybrid mode Type B+ NVIDIA RTX A4500 with MXM 3.1 TYPE B+ form factor(82 x 105 mm). Up to 5888 CUDA cores , 46 RT cores and 184 Tensor cores, 17.66 TFLOPS. GDDR6 16GB memory, 256-bit, bandwidth 512 GB/s. Up to 4 x DisplayPort 1.4a outputs. Long life cycle, supports 5 years availability.
NVIDIA Jetson Orin NX 16G Lite AI System_Super Fanless and ultra-compact design. Embedded with NVIDIA® Jetson Orin™ NX up to 157 TOPS. Support 1 x GbE, 2 x USB3.2 Gen1 (5Gbit/s). Support 1 x mPCIe, 1 x M.2 3052, 1 x M.2 2280. Supports Allxon 24/7 remote monitoring and OTA deployment. Supports Super mode with Jetpack 6.2 and above.
Tesla H200 NVL 141GB PCIe DSFH w/ATX BKT NVIDIA Hopper GPU architecture. Compute-optimized GPU. 14,592 NVIDIA® CUDA® Cores. 456 NVIDIA® Tensor Cores. 141GB HBM3 memory with ECC. Up to 4.8 TB/s memory bandwidth. Max. power consumption: 600W. Graphics bus: PCI-E 5.0 x16. Thermal solution: Passive.
Quadro A1000 MXM 4GB Ms Hybrid mode Type A NVIDIA RTX A1000 with MXM 3.1 TYPE A form factor (82 x 70 mm). Up to 2048 CUDA cores , 16 RT cores and 64 Tensor cores, 6.66 TFLOPS. GDDR6 4GB memory, 128-bit, bandwidth 224 GB/s. Up to 4 x DisplayPort 1.4a outputs. Long life cycle, supports 5 years availability.
Quadro A1000 MXM 4GB Discrete mode Type A 35W NVIDIA RTX A1000 with MXM 3.1 TYPE A form factor (82 x 70 mm). Up to 2048 CUDA cores , 16 RT cores and 64 Tensor cores, 6.66 TFLOPS. GDDR6 4GB memory, 128-bit, bandwidth 224 GB/s. Up to 4 x DisplayPort 1.4a outputs. Long life cycle, supports 5 years availability.
Quadro 5000 Ada MXM 16GB MS-Hybrid mode Type B+ NVIDIA RTX 5000 Ada Generation with MXM 3.1 TYPE B+ form factor(82 x 105 mm). Up to 9728 CUDA cores , 76 RT cores and 304 Tensor cores, 42.6 TFLOPS. GDDR6 16GB memory, 256-bit, bandwidth 576 GB/s. Discrete or MS-Hybrid mode supported. Memory Error Correction Code (ECC) supported. Encode Sessions Unlimited....
RTX PRO 6000 Blackwell Max-Q PCIe 96GB DSFH NVIDIA Blackwell GPU architecture. AI Performance 3511 TOPS. Single-Precision (FP32) Performance 110 TFLOPS. 24,064 CUDA cores. 96GB GDDR7 memory with ECC. 4.4” H x 10.5”L, FHFL Dual Slot. Max Power Consumption: 300W. 4 x Multi-instance GPU (MIG). 4 x DisplayPort 2.1.
Quadro A2000 MXM 8GB MS Hybrid mode Type A NVIDIA® RTX™ A2000 with MXM 3.1 TYPE A form factor(82 x 70 mm). Up to 2560 CUDA cores , 20 RT cores and 80 Tensor cores, 8.64 TFLOPS. GDDR6 4GB memory, 128-bit, bandwidth 192 GB/s. Up to 4 x DisplayPort 1.4a outputs. Long life cycle, supports 5 years availability.
Quadro 2000 Ada MXM 8GB MS Hybrid mode Type A NVIDIA Ada-Lovelace architecture Quadro® 2000A with MXM 3.1 TYPE A form factor (82 x 70 mm). Up to 3072 CUDA cores, 24 RT cores and 96 Tensor cores, 12.99 TFLOPS. GDDR6 8GB memory, 128-bit, bandwidth 256 GB/s. Discrete or MS-Hybrid mode supported. Memory Error Correction Code (ECC) supported. Encode Sessions...
Quadro A800 Active PCIe 40GB DSFH w/ATX BKT BULK NVIDIA Ampere GPU architecture. Compute-optimized GPU with Active Fan. 6912 NVIDIA® CUDA® Cores / 432 NVIDIA® Tensor Cores. 40GB HBM2 memory with ECC. 1.5TB/s memory bandwidth. NVLink Bandwidth : 400GB/s. Max. power consumption: 300W. Graphics bus: PCI-E 4.0 x16. PN : SKY-QUAD-A800-40.
Quadro RTX 2000 Ada PCIe 16GB DSLP w/ATX BKT NVIDIA Ada Lovelace GPU architecture. Fourth-generation Tensor Cores. Third-generation RT Cores. GDDR6 memory with ECC. AV1 Encode and Decode Support. NVIDIA GPUDirect Remote Direct Memory Access (RDMA) support. NVIDIA Mosaic Technology. Graphics bus: PCI-E 4.0 x16. PN：SKY-QUAD-2000A-16.
Quadro T1000 MXM 4GB MS Hybrid mode Type A NVIDIA® Quadro® T1000 with MXM 3.1 TYPE A form factor(82 x 70 mm). Up to 896 CUDA cores , 2.6 TFLOPS. GDDR6 4GB memory, 128-bit, bandwidth 192 GB/s. Up to 4 x DisplayPort 1.4a outputs. Long life cycle, supports 5 years availability.
Tesla H100 80GB PCIe DSFH w/ATX BKT NVIDIA Hopper GPU architecture. Compute-optimized GPU. 14592 NVIDIA® CUDA® Cores. 456 NVIDIA® Tensor Cores. 80GB HBM2e memory with ECC. Up to 2TB/s memory bandwidth. Max. power consumption: 350W. Graphics bus: PCI-E 5.0 x16. Thermal solution: Passive.
Quadro T1000 MXM 4GB Discrete mode Type A NVIDIA® Quadro® T1000 with MXM 3.1 TYPE A form factor(82 x 70 mm). Up to 896 CUDA cores , 2.6 TFLOPS. GDDR6 4GB memory, 128-bit, bandwidth 192 GB/s. Up to 4 x DisplayPort 1.4a outputs. Long life cycle, supports 5 years availability.
Tesla L40S 48GB PCIe DSFH w/ATX BKT NVIDIA Ada-Lovelace GPU architecture. Universal Compute & Graphics GPU. 18176 NVIDIA® CUDA® Cores. 568 NVIDIA® Tensor Cores; 142 NVIDIA® RT Cores. 48GB with ECC memory. Up to 864 GB/s memory bandwidth. Max. power consumption: 350W. Graphics bus: PCIe 4.0 x16. SKY-TESL-L40S-48P.
Tesla L40 48GB PCIe DSFH w/ATX BKT NVIDIA Ada-Lovelace GPU architecture. Universal Compute & Graphics GPU. 18176 NVIDIA® CUDA® Cores. 568 NVIDIA® Tensor Cores; 142 NVIDIA® RT Cores. 48GB with ECC memory. Up to 864 GB/s memory bandwidth. Max. power consumption: 300W. Graphics bus: PCIe 4.0 x16. Thermal solution: Passive.
Quadro T1000E PCIe 8GB SSLP w/ATX BKT BULK NVIDIA Turing GPU architecture. NVIDIA Long-life SKU, Product Life Extended Until 2029. 896 NVIDIA® CUDA® Cores. 8 GB GDDR6 Memory. 160GB/s Memory Bandwidth. Max. Power Consumption: 50W. Graphics Bus: PCI-E 3.0 x16. Thermal Solution: Active. Display Connectors: mDP 1.4.
Quadro T600E PCIe 4GB SSLP w/ATX bracket BULK NVIDIA Turing GPU architecture. NVIDIA Long-life SKU, Product Life Extended Until 2029. 640 NVIDIA® CUDA® Cores. 4 GB GDDR6 Memory. 160 GB/s Memory Bandwidth. Max. Power Consumption: 40. Graphics Bus: PCI-E 3.0 x16. Thermal Solution: Active. Display Connectors: mDP 1.4.
Quadro RTX A4000E PCIe 16GB SSFH w/ATX BKT BULK NVIDIA® Ampere GPU architecture. NVIDIA Long-life SKU, Product Life Extended Until 2029. 6,144 NVIDIA® CUDA® Cores. 192 NVIDIA® Tensor Cores. 48 NVIDIA® RT Cores. 16GB GDDR6 memory with ECC. Max. power consumption: 140W; Graphics bus: PCI-E 4.0 x16. Thermal solution: active; Display connectors: DP 1.4a.
Quadro RTX A1000 PCIe 8GB SSLP w/ATX Bracket BUL NVIDIA Ampere GPU architecture. 2,304 NVIDIA® CUDA® Cores. 72 NVIDIA® Tensor Cores (3rd gen). 18 NVIDIA® RT Cores (2nd gen). 8GB GDDR6 memory. Up to 192GB/s memory bandwidth. Max. power consumption: 50W. Graphics bus: PCI-E 4.0 x8. Display connectors: mDP 1.4a.
Tesla A30 24GB PCIe DSFH w/ATX BKT NVIDIA Ampere GPU architecture. Compute-optimized GPU. 3584 NVIDIA® CUDA® Cores. 224 NVIDIA® Tensor Cores. 24GB HBM2 memory with ECC. UP to 933 GB/s memory bandwidth. Max. power consumption: 165W. Graphics bus: PCI-E 4.0 x16. Thermal solution: Passive.
2U GPU Server,dual Intel SPR-SP w/2.7KW RPS Processor: Dual 4th/5th Gen Intel Xeon Scalable processors. Memory: 16 x DDR5 4800MHz ECC RDIMM/ Intel Optane DC Persistance Memory, up to 2TB. Remote Management: IPMI function support. Expansion: Supporting 4 x PCIe x16 double width cards + 2 x PCIe x16 double width cards or 4 x PCIe x8 single width FH/10.5" +...
Quadro RTX A400 PCIe 4GB SSLP w/ATX Bracket BULK NVIDIA Ampere GPU architecture. Third-generation Tensor Cores. Second-generation RT cores. GDDR6 memory. AV1 Decode Support. Max. power consumption: 50W. Graphics bus: PCI-E 4.0 x8. Thermal solution: Active. Display connectors: mDP 1.4a.
Quadro RTX 2000E Ada PCIe 16GB SSLP w/ATX BKT NVIDIA Ada Lovelace GPU architecture. 2,816 NVIDIA CUDA Cores. 88 Tensor Cores (4th gen). 22 RT Cores (3th gen). GDDR6 memory with ECC. NVIDIA GPUDirect Remote Direct Memory Access (RDMA) support. Long life availability. Graphics bus: PCI-E 4.0 x8.
Quadro 5000 Ada MXM 16GB Discrete mode Type B+ NVIDIA® Quadro® 5000 Ada with MXM 3.1 TYPE B+ form factor(82 x 105 mm). Up to 9728 CUDA cores , 76 RT cores and 304 Tensor cores, 42.6 TFLOPS. GDDR6 16GB memory, 256-bit, bandwidth 576 GB/s. Discrete or MS-Hybrid mode supported. Memory Error Correction Code (ECC) supported. Encode Sessions Unlimited....
