NVIDIA Tesla V100 16GB 16GB Specs, Benchmarks & Pricing

• Release Date: June 21, 2017
• MSRP: $10,000 USD
• GPU Architecture: volta
• Hardware-Accelerated GEMM Operations:
  FP64 FP32 TF32 BF16 FP16 FP8 FP4 INT8 INT4
• CUDA Compute Capability : 7

Specifications for NVIDIA Tesla V100 16GB

References

• https://developer.nvidia.com/blog/inside-volta/
• https://www.nvidia.com/en-us/data-center/v100/
• https://images.nvidia.com/content/tesla/pdf/Tesla-V100-PCIe-Product-Brief.pdf
• https://resources.nvidia.com/en-us-virtualization-and-gpus/v100-datasheet
• https://www.tomshardware.com/news/nvidia-tesla-v100-volta-gpu,34379.html
• https://www.microway.com/knowledge-center-articles/in-depth-comparison-of-nvidia-tesla-volta-gpu-accelerators/
• https://www.nvidia.com/en-us/data-center/tensor-cores/
• https://www.microway.com/hpc-tech-tips/nvidia-tesla-v100-price-analysis/
• https://www.nextplatform.com/2018/03/05/tesla-gpu-accelerator-bang-buck-kepler-volta/
• https://govindhtech.com/nvidia-tesla-v100-price-and-specifications/
• https://www.8anet.com/Product/16529/NVIDIA-900-2G500-0000-000-Tesla-V100-GPU-for-PCIe-16GB-HBM2-640-Tensor-Cores-Passive-Cooling
• https://pcserverandparts.com/dell-nvidia-tesla-v100-16gb-hmb2-graphics-accelerator-card-used-vfj45/
• http://accessories.dell.com/sna/productdetail.aspx?c=us&l=en&s=gov&sku=490-BENS
• https://www.itcreations.com/product/106306
• https://www.amazon.com/HP-nVidia-876340-001-876908-001-Q2N68A/dp/B07DJYQ5W7
• https://itprice.com/hp/q2n68a.html
• https://www.provantage.com/lenovo-4c57a09498~7LEN9QJC.htm
• https://serverproven.lenovo.com/option/4C57A09498/
• https://www.provantage.com/lenovo-4x67a11524~4LEN9QMR.htm
• https://www.exxactcorp.com/PNY-TCSV100MPCIE-PB-E1584138
• https://www.amazon.com/PNY-TCSV100MPCIE-PB-Nvidia-Tesla-v100/dp/B076P84525
• https://www.newegg.com/p/17Z-000E-001W6
• https://www.wiredzone.com/shop/product/10027795-supermicro-gpu-nvtv100-16-nvidia-tesla-v100-16gb-cowos-hbm2-pcie-3-0-passive-cooling-1891
• https://www.connection.com/product/cisco-nvidia-tesla-v100-pcie-gpu-16gb/ucsc-gpu-v100/35528075
• https://www.techpowerup.com/gpu-specs/tesla-v100-pcie-32-gb.c3184
• https://images.nvidia.com/content/volta-architecture/pdf/volta-architecture-whitepaper.pdf
• https://www.nvidia.com/en-au/data-center/v100/

Notes

1. int8TOPS: from https://www.microway.com/knowledge-center-articles/in-depth-comparison-of-nvidia-tesla-volta-gpu-accelerators/
2. supportedCUDAComputeCapability: lookup GPU Compute Capability at https://developer.nvidia.com/cuda-gpus
3. Estimated MSRP of $10,000 USD for Tesla V100 16GB PCIe based on launch-time market pricing. NVIDIA does not publish official MSRP for data center GPUs. Multiple sources from 2017-2018 cite pricing in the $8,000-$10,664 range: Microway's price analysis lists single-unit list price at $10,664, CDW retailer pricing from March 2018 at $9,900 (per Next Platform), and general tech sources cite launch range of $8,000-$10,000. Note: Pricing varies by form factor (PCIe vs SXM2) and purchase volume.
4. Product SKU 'PG500 SKU 200' sourced from TechPowerUp GPU Database and multiple reseller listings showing Board Number PG500 SKU 200
5. Board ID PG500 sourced from eBay listings and reseller product descriptions
6. NVIDIA part number (NVPN) 900-2G500-0000-000 sourced from 8anet.com, Exxact, Amazon, and multiple authorized resellers. This is the primary NVPN for the passive-cooled PCIe reference design
7. NVIDIA reference design part number 699-2G500-0200-xxx sourced from multiple OEM listings. The 'xxx' suffix varies by OEM (e.g., -300, -310, -320)
8. Dell part number VFJ45 (0VFJ45) sourced from pcserverandparts.com, shop.bytestock.com, and itcreations.com
9. Dell SKU 490-BENS sourced from Dell official accessories portal (accessories.dell.com)
10. Dell OEM part number 900-2G500-0100-030 sourced from piospartslap.de and itcreations.com
11. Dell OEM part number 699-2G500-0200-300 sourced from harddiskdirect.com, itcreations.com, and multiple resellers
12. HPE part number Q2N68A sourced from Amazon, itprice.com, and expresscomputersystems.com. This is the primary HPE SKU
13. HP part number 876340-001 (PCI-e PN) sourced from Amazon and compeve.com
14. HP part number 876908-001 (Spare PN) sourced from Amazon, Newegg, and newtownspares.com
15. HP OEM part number 900-2G500-0300-030 sourced from Newegg and compeve.com
16. Lenovo part number 4C57A09498 sourced from provantage.com and Lenovo ServerProven (serverproven.lenovo.com)
17. Lenovo part number 4X67A11524 sourced from provantage.com and itosolutions.net
18. PNY SKU TCSV100MPCIE-PB sourced from Exxact, Amazon (ASIN B076P84525), and ebuyer.com
19. Supermicro part number GPU-NVTV100-16 for PCIe version sourced from Newegg, Wiredzone, and smicro.eu
20. Supermicro part number GPU-NVTV100-SXM2 for SXM2 version with NVLink sourced from Exxact and SabrePC
21. Cisco part number UCSC-GPU-V100= sourced from connection.com, macconnection.com, and consutronix.com
22. supportedHardwareOperations corrected 2026-09-02 to the canonical Volta baseline (FP16 only) documented in .claude/agents/gpu-researcher.md, sourced from the NVIDIA Tesla V100 GPU Architecture whitepaper (images.nvidia.com/content/volta-architecture/pdf/volta-architecture-whitepaper.pdf): "Tensor Cores operate on FP16 input data with FP32 accumulation." Removed FP64, FP32, and INT8 — Volta's 1st-generation Tensor Cores support only FP16-in/FP32-accumulate matrix multiply; there is no INT8/INT4 Tensor Core path (added in Turing), no TF32/BF16 (Ampere), no FP8 (Ada), and no FP64 Tensor Core path (added in Ampere's A100). The int8TOPS value of 56 that remains on this file reflects V100's DP4A 4-element dot-product ALU instruction, a plain CUDA-core path (not a Tensor Core/GEMM path), the same distinction already applied to Pascal Tesla P4/P40 DP4A support in the canonical table — so it is retained as a numeric spec but INT8 is correctly excluded from supportedHardwareOperations under the GEMM-only definition.
23. fp8TFLOPS and fp4TFLOPS are null: Volta predates both FP8 (introduced in Ada) and FP4 (introduced in Blackwell) Tensor Core support. Confirmed hardware negative per the NVIDIA Tesla V100 GPU Architecture whitepaper, which documents only FP16 Tensor Core input support. Not added to unverifiedSpecs since these are confirmed negatives, not data gaps.
24. CORRECTED 2026-09-02: maxTDPWatts changed from 300W to 250W. This file describes the PCIe form factor (confirmed by the cited Tesla-V100-PCIe-Product-Brief.pdf reference, the PCIe-specific thirdPartyProducts part numbers, and the summary text), and 300W is the SXM2 TDP, not PCIe. NVIDIA's official V100 product page (nvidia.com/en-au/data-center/v100/) lists Maximum Power Consumption / TDP as 300W for "V100 for NVLink (SXM-2)" versus 250W for "V100 for PCIe" — matching the 250W figure independently confirmed in the Tesla-V100-PCIe-Product-Brief.pdf Thermal Specifications table (Table 5, Total Board Power).
25. CORRECTED 2026-09-02: fp16TFLOPS changed from 28 to 112. The prior value of 28 was the plain vector/non-tensor FP16 rate (2x FP32's 14 TFLOPS), not the Tensor Core path required by this project's fp16TFLOPS convention (use the matrix/tensor AI-accelerator path, not the SIMD vector path; see .claude/agents/gpu-researcher.md and project memory). NVIDIA's official V100 product page (nvidia.com/en-au/data-center/v100/) specs table lists Deep-Learning/Tensor FP16 performance as 125 TFLOPS for "V100 for NVLink (SXM-2)" versus 112 TFLOPS for "V100 for PCIe (32 GB)" — the PCIe row also lists FP32=14.0 TFLOPS and FP64=7.0 TFLOPS, matching this file's existing fp32TFLOPS=14 value and confirming this file describes the original (non-V100S) PCIe variant. Cross-validated against Microway's independently sourced comparison table (microway.com/knowledge-center-articles/in-depth-comparison-of-nvidia-tesla-volta-gpu-accelerators/), which lists "TensorFLOPS, 125 TFLOPS [SXM2], 112 TFLOPS [PCIe]" and "Integer Operations (INT8)*, 62.8 TOPS [SXM2], 56 [PCIe]" — the INT8 figure of 56 matches this file's existing int8TOPS value, further confirming the PCIe column is the correct one for this SKU.