Quick wins for a faster PC:
Scan for outdated or missing drivers - takes under a minuteDriver Scan →Repair Windows errors before they cause bigger problemsFix Now →Fix the driver behind crashes, sound loss and screen glitchesFind Drivers →Some links on this page are affiliate links: if you buy through them we may earn a commission, at no extra cost to you.
NVIDIA received U.S. authorization to continue specified H100 development work in 2022, but its public filing did not say the company could manufacture H100 chips in mainland China or sell them there without restriction. The authorization also covered limited logistics through Hong Kong. Those were narrower permissions than the claim that NVIDIA could keep manufacturing and selling H100s in China despite an export ban.
What the U.S. restricted in August 2022
On August 26, 2022, NVIDIA disclosed that the U.S. government had imposed an immediate license requirement for future exports of its A100 and forthcoming H100 chips to China—including Hong Kong—and Russia. The restriction also covered systems incorporating those chips, such as NVIDIA DGX systems, and certain technology used to support or develop the products. NVIDIA’s August 26 filing and its 2022 quarterly filing describe the requirements and their potential scope.
The U.S. cited concerns involving military end use, military end users and diversion of advanced computing capabilities. A license requirement is not quite the same as a rule saying every related activity is categorically forbidden: a covered transaction generally needs authorization. But without the required license, an export covered by the rule cannot proceed lawfully.
Free tools Windows power users keep installed
One-click scans. No signup required.
NVIDIA warned that the new requirement could affect its ability to complete H100 development and support A100 customers. It said it might need to move some operations out of China. That warning concerned the impact of controls on development and support activities as well as exports—not proof that finished H100 chips were being fabricated in China.
#1 Best Overall
- PLEASE NOTE: Exporting an NVIDIA RTX Pro 6000 GPU outside the US requires strict adherence to the U.S. Export Administration Regulations (EAR) and issuance of an export license from the Bureau of Industry and Security (BIS). Compliance and Know Your Customer (KYC) screening may be required as a condition of order acceptance. [NVIDIA Blackwell Streaming Multiprocessor] The new SM features increased processing throughput, and new neural shaders that integrate neural networks inside of programmable shaders | DLSS 4: Multi Frame Generation ensures ultra-smooth frame pacing for lifelike simulations.
- [Double-Flow-Through Design] The RTX PRO 6000 Blackwell features a double-flow-through cooling design, optimizing efficiency and airflow to sustain peak performance under 600W power loads. | [5th Gen Tensor Cores] Deliver up to 3X the performance of the previous generation and support for FP4 precision for faster AI model processing times with reduced memory usage, enabling local fine-tuning of LLMs and generative AI | [4th Gen Ray Tracing Cores] Double the ray-triangle intersection rate of the previous generation to create photoreal, physically accurate scenes and immersive 3D designs with RTX Mega Geometry, which enables up to 100X more ray-traced triangles.
- [PCIe Gen 5] Support for PCIe Gen 5 provides double the bandwidth of PCIe Gen 4, improving data-transfer speeds from CPU memory and unlocking faster performance for data-intensive tasks like AI, data science, and 3D modeling. | [GDDR7 Memory] With 96 GB of GPU memory and 1.8 TB ps bandwidth, it can tackle massive 3D and AI projects, fine-tune AI models locally, explore large-scale VR environments, and drive larger multi-app workflows.
- [DisplayPort 2.1] Achieve unparalleled visual clarity and performance, driving high resolution displays at up to 8K at 240 Hz and 16K at 60 Hz. Increased bandwidth enables seamless multi-monitor setups while HDR and higher color depth support ensures superior color accuracy for precision work, such as video editing, 3D design, and live broadcasting.
- [Universal MIG] Divide a single RTX PRO 6000 Blackwell into multiple isolated instances, each with dedicated resources, allowing for concurrent execution of multiple workloads, optimized GPU utilization, and secure isolation of different applications or users. [WARRANTY] 3 YR Manufacturer's Warranty. Bulk OEM Packaging. Retail Packaging is NOT included.
What NVIDIA was allowed to do
On September 1, 2022, NVIDIA disclosed that the U.S. government had authorized exports, reexports and in-country transfers needed to continue the company’s development of H100 integrated circuits. The filing also described a separate, time-limited authorization for A100 and H100 order fulfillment and logistics through NVIDIA’s Hong Kong facility, running until September 1, 2023. A100 customer support was separately authorized through March 1, 2023. The September 1 filing sets out these distinct permissions.
That distinction matters. Authorization to move technology or other items needed for development does not automatically authorize commercial exports of finished chips. Nor does permission for logistics through Hong Kong establish that any Chinese customer could receive H100 hardware. Licenses can be limited by product, activity, destination, end user or end use.
Rank #2
- NVIDIA Ampere Architecture-based CUDA Cores - Double-speed processing for single-precision floating point (FP32) operations and improved power efficiency provide significant performance improvements for graphics and simulation workflows, such as complex 3D computer-aided design (CAD) and computer-aided engineering (CAE), on the desktop.
- Second-Generation RT Cores - With up to 2X the throughput over the previous generation and the ability to concurrently run ray tracing with either shading or denoising capabilities, second-generation RT Cores deliver massive speedups for workloads like photorealistic rendering of movie content, architectural design evaluations, and virtual prototyping of product designs. This technology also speeds up the rendering of ray-traced motion blur for faster results with greater visual accuracy.
- Third-Generation Tensor Cores - New Tensor Float 32 (TF32) precision provides up to 5X the training throughput over the previous generation to accelerate AI and data science model training without requiring any code changes. Hardware support for structural sparsity doubles the throughput for inferencing. Tensor Cores also bring AI to graphics with capabilities like DLSS, AI denoising, and enhanced editing for select applications.
- Third-Generation NVIDIA NVLink - Increased GPU-to-GPU interconnect bandwidth provides a single scalable memory to accelerate graphics and compute workloads and tackle larger datasets.
- 48 Gigabytes (GB) of GPU Memory - Ultra-fast GDDR6 memory, scalable up to 96 GB with NVLink, gives data scientists, engineers, and creative professionals the large memory necessary to work with massive datasets and workloads like data science and simulation.
Development is not the same as manufacturing
- Development means work involved in creating and refining a product. Depending on the activity, this can involve engineering, testing, validation or related technology transfers.
- Manufacturing means producing the chip—for example, fabricating it or assembling and packaging it. NVIDIA’s September 2022 filing does not say that H100 chips were fabricated in mainland China or that the company received permission for unrestricted production there.
- Export or sale concerns transferring a product to a destination or customer. Those transactions remained subject to applicable U.S. licensing rules, regardless of where a chip was made.
- Logistics concerns handling and routing orders. The Hong Kong authorization was limited in scope and time; it was not a general sales exemption.
These are separate questions. A chip could be made in one country and still be restricted from export to a particular customer elsewhere. Likewise, development work in a country does not establish that finished chips are manufactured there. The public filing supports a narrow claim about continued development and certain logistics—not the stronger claim in the original headline.
Could NVIDIA sell H100 chips to Chinese customers?
The September 2022 authorization did not announce unrestricted H100 sales in China. Future exports of A100 and H100 to China were subject to a license requirement, and the filing describing the development authorization does not say that broad commercial sales had been approved. A specific transaction could depend on its license, destination, customer, end use and product classification; the public disclosures do not establish the status of every possible transaction.
Rank #3
- NVIDIA Volta GV100 Architecture — 4,608 CUDA Cores, 640 1st-Gen Tensor Cores delivering 14 TFLOPS FP32 and 112 TFLOPS deep learning performance for AI training, inference, HPC, and scientific computing workloads
- 32GB HBM2 ECC Memory — 900 GB/s Bandwidth — High-bandwidth memory on a 4096-bit bus with ECC error correction provides the memory capacity and throughput required for the largest AI models, simulations, and datasets
- PCIe 3.0 x16 Interface — 250W TDP — Standard PCIe Gen3 connectivity with passive cooling designed for enterprise rack server deployment in HPE ProLiant, Dell PowerEdge, and Supermicro platforms with adequate chassis airflow
- NVLink — Scale to 96GB Unified Memory — Connect two V100 GPUs via NVLink at 300 GB/s bi-directional bandwidth to scale GPU memory from 32GB to 96GB for larger AI training and HPC workloads
- Multi-Precision Computing — Supports FP64 (7 TFLOPS), FP32 (14 TFLOPS), FP16 (112 TFLOPS) and INT8 precision modes for flexible deployment across training, inference, and scientific simulation workloads
Hong Kong was not an automatic route around the controls. NVIDIA’s initial disclosure included Hong Kong in the China-related restrictions, and the later logistics permission had a stated expiration date. Routing, billing or processing a transaction through another place does not by itself decide whether an export is allowed; destination and end user can still matter under export-control rules.
Independent reader supportYour contribution helps us test, update, and keep practical guides available for everyone.How the restrictions changed after 2022
The 2022 controls were not the end of the story. The U.S. added restrictions in July 2023 and issued broader, performance-based controls in October 2023. NVIDIA’s subsequent filings describe continuing licensing requirements affecting advanced products and report that the company moved certain testing, validation, supply and distribution operations out of China and Hong Kong. See NVIDIA’s July 2023 filing, its July 2024 filing and the Bureau of Industry and Security’s export-controls information.
Rank #4
- Standard Memory: 40 GB
- Host Interface: PCI Express 4.0
- Cooler Type: Passive Cooler
- Product Type: Graphics Card
NVIDIA tried to preserve access to the Chinese market with products designed or modified to meet applicable U.S. thresholds. Earlier filings discuss the A800 as an alternative; later filings describe China-specific products and the commercial effects of expanding restrictions. But a product designed to fit one set of rules can be affected when those rules change. NVIDIA’s filings continued to identify the H100 among products subject to China-related export controls, including in 2026. The company’s 2026 annual filing and April 2026 quarterly filing do not verify ongoing H100 manufacturing in mainland China.
What this means for NVIDIA’s China business
The controls put NVIDIA between U.S. national-security policy and the commercial importance of the Chinese market. Product changes may preserve some access, but restrictions can limit which chips can be sold, require redesign work and change the company’s competitive position. NVIDIA’s disclosures describe those constraints and its operational adjustments; they do not support a claim that H100 sales or production in China continued freely.
It is also important to separate authorized sales from reports of third-party or gray-market access to restricted hardware. The existence of a chip in a market would not, by itself, show that NVIDIA had permission to sell it there. Export controls can apply to software, technology, systems and support as well as physical chips, and enforcement or diversion questions are distinct from the scope of NVIDIA’s authorization.
Quick Recap
Product prices and availability are accurate as of the date/time indicated and are subject to change. Any price and availability information displayed on Amazon at the time of purchase will apply.
