Price for 6000 Blackwell series cards have stabilized after 3 consecutive 30% baseline hikes by Nvidia in 2026 and are expected to maintain through the rest of 2026. Supply remains strained. Please note that compliance is mandatory on all AI enterprise compute GPUs and Servers and end-user forms must be filled out before we can share any quotes. Please note Credit Card payments will only work if USD or AED currency is selected on top right corner of the website. HGX B200/B300 lead times are now between 8-14 weeks for Golden Sku, with custom BOMs exceed 20 weeks. For DRAM and SSD bulk orders, please inquire in the chat.
NVIDIA B200 Tensor Core GPU 192GB is a high-performance AI accelerator built on the NVIDIA Blackwell architecture, designed for large-scale AI training and inference. Featuring 192GB HBM3e memory, up to 8 TB/s memory bandwidth, and advanced Tensor Cores with FP4 and FP8 support, it delivers exceptional performance for generative AI, large language models (LLMs), and HPC workloads in modern data centers.
Verified reviews from real customers on Trustpilot
| Specification | NVIDIA B200 Tensor Core GPU 192GB |
|---|---|
| Architecture | Blackwell (GB200) |
| Transistors | 208 billion |
| Memory | 192GB HBM3e |
| Memory Bandwidth | Up to 8 TB/s |
| FP4 Tensor Core | Yes (Native) |
| FP8 Tensor Core | Yes (2nd Generation) |
| Transformer Engine | 2nd Generation |
| NVLink | 5th Generation (Up to 1.8 TB/s) |
| TDP | Up to 1000W |
| Manufacturing Process | TSMC 4NP |
No file available
No reviews available.