Recommended Free Tools
iTechGuides is reader-supported. When you buy through links on our site, we may earn an affiliate commission. As an Amazon Associate I earn from qualifying purchases. Learn more
Pat Gelsinger’s “10,000× too expensive” remark was an estimate about the efficiency needed to make AI inference economical at scale—not evidence that NVIDIA GPUs are literally priced 10,000 times above a comparable alternative. He later said the figure came from his own calculations about search-related energy, compute, and cost, but did not provide the calculation or an independently verified benchmark.
What Gelsinger said about inference costs
In a March 22, 2025 report, HotHardware quoted former Intel CEO Pat Gelsinger saying a GPU was “way too expensive” and that it was “10,000x too expensive to fully realize what we want to do with the deployment of inferencing for AI.” The remark was reported as coming from his appearance on the Acquired podcast at NVIDIA’s GTC 2025 conference. HotHardware’s report attributes the quote to Gelsinger; it does not establish a comparison between the price of a particular GPU and a specific rival chip.
In a 2026 interview, Gelsinger explained that “10,000x” was “sort of a number that I pulled out based on some math of where search was in terms of energy, compute, cost.” The interview does not supply the underlying calculation. That clarification supports reading the figure as his estimate of the scale of improvement he believes inference economics may require—not as a measured statistic or a literal product-price ratio. Read the 2026 interview.
The Tool Desk
Outbyte Driver Updater FREEScan for outdated or missing drivers - takes under a minuteDriver Scan →Outbyte PC Repair FREEClear out junk files and repair common Windows errorsFree Scan →Why he distinguishes training from inference
Gelsinger described GPUs as strong for training and useful for part of the transition from training into inference, but said they are “not an optimized inference chip.” The distinction is about workload fit: a device designed to perform well in one stage of AI computing is not automatically the most efficient choice for serving model outputs at scale. His comments argue for better inference economics, not for abandoning GPUs altogether.
#1 Best Overall
- System Compatibility Note: This 2-slot card measures 271 x 112 x 39 mm and requires a single 12V-2x6-pin power connector. Please verify chassis and PSU compatibility before purchase.
- Dedicated Support: Please contact us directly through Amazon for any product questions or assistance you may require.
- Professional Intel Arc Pro B70 GPU: Built on the Intel Xe2-HPG architecture, it features 32 Xe cores and 256 XMX engines, designed to accelerate AI, rendering, and complex visualization workloads.
- Massive 32GB GDDR6 VRAM: Equipped with 32GB of high-speed GDDR6 memory on a 256-bit bus, running at 19 Gbps, which allows for handling large AI models and complex datasets locally.
- High-Performance Engine Clock: Delivers an engine clock of 2540 MHz, providing the compute power needed for demanding professional applications and AI inference.
The 2025 report did not identify a replacement architecture that Gelsinger endorsed. It mentions NPUs and ASICs as possibilities, but that is the reporter’s speculation, not a confirmed recommendation from Gelsinger.
What “NVIDIA got lucky” means in context
The “got lucky” wording refers to a discussion of NVIDIA’s early commitment to throughput computing and how that strategy later aligned with AI workloads. It is provocative shorthand for a favorable shift in what the market needed; the report does not show that chance alone explains NVIDIA’s success. Nor does the phrase establish that GPUs are unsuitable for AI. Gelsinger’s separate point is that their strengths do not make them optimized for every inference task.
Rank #2
- 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
How to evaluate inference hardware claims
A useful comparison must hold the workload and model constant. A headline ratio without a stated baseline, task, or measurement method cannot show whether one accelerator is a better choice for a particular deployment.
Do these 3 things before closing this tab:
1Scan for outdated or missing drivers - takes under a minute2Repair Windows errors before they cause bigger problems3Fix the driver behind crashes, sound loss and screen glitches- Throughput: Report aggregate output and, for generative AI, tokens per second.
- Latency: Measure how long users wait for responses, rather than inferring responsiveness from peak throughput.
- Efficiency: Compare tokens per second per watt under the same workload and conditions.
- Total cost: Tie cost claims to a defined deployment and baseline, including the amount of work delivered.
- Deployment constraints: Account for software and operational requirements alongside hardware performance.
In the 2026 interview, Gelsinger named tokens per second, tokens per second per watt, aggregate throughput, and latency as measures for judging architecture performance. The cited sources provide no product-level results across these measures, so they cannot establish which specific GPU or alternative accelerator wins.
Quick Recap
Best Value
- 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.
Rank #4
- System Compatibility Note: 2-slot card, 271x112x39mm, single 8-pin power, 200W TDP. Verify chassis clearance and PSU capacity before purchase.
- Dedicated Support: Please contact us directly through Amazon for any product questions or assistance you may require.
- 24GB GDDR6 on 192-Bit Bus: Massive 24GB memory with 456 GB/s bandwidth – ideal for LLMs, AI inference, 3D rendering, and generative design.
- Intel Xe2-HPG Architecture: Built on Intel's next-gen architecture with 20 Xe cores and 160 XMX engines for AI acceleration (197 INT8 TOPS).
- PCIe 5.0 Support: PCI Express 5.0 x16 interface for maximum bandwidth with the latest workstation platforms.
Rank #3
- Professional AI & Creator Workstation: AMD Radeon AI PRO R9700 GPU with 32GB GDDR6 is engineered for AI development, professional content creation, and compute-intensive workloads.
- Massive 32GB Memory Capacity: 32GB of GDDR6 memory on a 256-bit bus provides ample bandwidth for large AI models, 8K video editing, and complex 3D rendering.
- Advanced RDNA 4 with AI Accelerators: 64 Compute Units with 3rd Gen Ray Tracing and dedicated 2nd Gen AI Accelerators for groundbreaking AI performance and visual computing.
- Professional Blower Cooling: Efficient single blower design exhausts heat directly out of the chassis, ideal for multi-GPU workstation and server configurations.
- Enterprise-Grade Thermal Solution: Vapor chamber heatsink with industrial Honeywell PTM7950 thermal interface material ensures reliable cooling under sustained professional loads.
What the 10,000× figure does—and does not—prove
- It does express Gelsinger’s view that far better economics are needed for inference to scale.
- It does not establish that NVIDIA GPU prices are literally 10,000 times too high.
- It is not an independently published GPU-versus-inference-chip efficiency or price benchmark.
- It does not identify a specific replacement processor or prove that one architecture is best for every inference workload.
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.
