NVIDIA A100 80GB
Ampere Tensor Core GPU with 80 GB HBM2e and 2 TB/s memory bandwidth. The proven workhorse for AI training, HPC, and data analytics with Multi-Instance GPU (MIG) for secure partitioning.
Showing all 7 results
-
-
NVIDIA B200
Blackwell architecture flagship — 192GB HBM3e, 8 TB/s bandwidth, up to 18 PFLOPS FP4 sparse per GPU. The next generation of AI training and inference.
-
NVIDIA H100 NVL
Dual-GPU PCIe accelerator with 94 GB HBM3 per card and an NVLink bridge delivering 600 GB/s GPU-to-GPU bandwidth. Purpose-built to supercharge LLM inference in mainstream PCIe servers.
-
NVIDIA H100 SXM
The GPU that launched the AI era — 80GB HBM3, 3.35 TB/s bandwidth, 3,958 TFLOPS FP8, NVLink 900 GB/s in an SXM form factor for HGX and DGX systems.
-
NVIDIA H200 NVL
The first PCIe GPU with HBM3e — 141 GB of memory at 4.8 TB/s. Hopper architecture with NVLink bridge, purpose-built to deploy large language models and generative AI in mainstream enterprise servers.
-
NVIDIA H200 SXM
Hopper architecture with HBM3e — 141GB memory, 4.8 TB/s bandwidth, up to 2x faster LLM inference vs H100. The memory-optimized AI GPU.
-
NVIDIA L40S
The universal Ada Lovelace GPU for the modern data center — 48 GB GDDR6 ECC, 18,176 CUDA cores, and 350W TDP delivering breakthrough performance for LLM inference, training, graphics, and video.