PerGB

NVIDIA Tesla V100 SXM2 16 GB

Live eBay prices, cheapest first. The best one right now is $195.00 (used).

Not a PCIe card. SXM module: needs an SXM-to-PCIe adapter board, its own cooling and power to run in a normal PC. The PCIe version: NVIDIA Tesla V100 PCIe 16 GB, from $325.00 → With its adapter board: NVIDIA Tesla V100 SXM2 16 GB mod kit, from $264.80 →

Other sizes: 32 GB

Specs

VRAM
16 GB HBM2
Bandwidth
900 GB/s
FP32
15.7 TFLOPS
FP16
125 TFLOPS
Power
300 W
Connector
SXM2 (PCIe 3.0)
Released
2017
CUDA compute
7.0
Llama 3.1 8B at Q4 (est.)
93–139 tokens/s

Volta: no longer supported by CUDA 13; CUDA 12 builds of PyTorch, vLLM and llama.cpp still run it.

Price right now

Live on eBay
Lowest now$195.00
Median ask$319.02
Per GB VRAM$12.19
vs launch price—
Live listings101

From the live listings below; shipping included.

Listings

Live on eBay
ListingConditionPriceChecked
Used$195.00−39%free shipping
Used$195.00−39%free shipping
Used$197.98−38%+$2.98 shipping
Used$200.00−37%+$5.00 shipping
Used$200.00−37%+$5.00 shipping
Used$200.00−37%+$5.00 shipping
Used$200.00−37%Check carefully+$5.00 shipping
Used$200.00−37%+$5.00 shipping
Used$203.20or best offer−36%+$5.00 shipping
Used$207.90−35%free shipping
Used$209.98or best offer−34%free shipping
Used$210.30or best offer−34%+$5.00 shipping
Used$215.88−32%free shipping
Used$218.03−32%free shipping
Used$219.00−31%free shipping
Used$221.55or best offer−31%free shipping
Used$223.56−30%+$80.00 shipping
Used$224.59or best offer−30%+$25.99 shipping
Used$224.98−29%+$3.00 shipping
Used$225.00−29%free shipping
Used$229.00−28%+$10.00 shipping
Used$231.03or best offer−28%+$14.99 shipping
Used$232.00or best offer−27%free shipping
Used$233.00or best offer−27%free shipping
Used$234.95or best offer−26%free shipping
Used$235.00or best offer−26%free shipping
Used$235.00or best offer−26%free shipping
Open box$237.48−26%free shipping
Used$237.99or best offer−25%free shipping
Used$240.00or best offer−25%free shipping
Used$249.00or best offer−22%free shipping
Used$249.98−22%free shipping
Used$250.00or best offer−22%free shipping
Used$284.85or best offer−11%+$38.88 shipping
Used$285.00−11%+$5.00 shipping
Used$286.00or best offer−10%+$80.00 shipping
Used$289.00−9%shipping not listed
Used$289.99−9%+$30.00 shipping
Open box$290.32−9%+$19.64 shipping
Open box$292.03−8%+$19.82 shipping
Open box$292.11−8%+$19.84 shipping
Used$292.99or best offer−8%free shipping
Used$294.99−8%+$45.99 shipping
Open box$297.00−7%+$20.00 shipping
Used$297.88−7%+$40.00 shipping
Used$299.98−6%free shipping
Used$299.98−6%+$40.00 shipping
Used$299.99−6%free shipping
Open box$301.78−5%+$3.00 shipping
Used$309.99+$30.00 shipping
Used$319.02+$2.00 shipping
Used$325.00free shipping
Used$335.00or best offer+$10.00 shipping
Used$339.72+$2.95 shipping
Used$349.99+$30.00 shipping
Used$350.00or best offerfree shipping
Used$350.00or best offerfree shipping
Used$356.99or best offer+$79.90 shipping
Used$359.98+$40.00 shipping
Used$360.00+$10.00 shipping

Showing the 60 cheapest of 101 listings.

Auctions ending soon

No auctions ending soon right now.

Prices include shipping and were read from eBay at the time shown. They can change: check the listing before you buy.

Owner reviews

No owner reviews yet. Own one? Tell others how it runs.

From signed-in owners, checked before they're published. PerGB doesn't pay for or edit reviews.

How it compares

Live on eBay

Faster, for the least

Compare: vs A40, vs RTX A6000, vs GeForce RTX 5080, vs Radeon RX 7900 XTX.

From the live listings of every GPU, shipping included; performance against the GeForce RTX 3090 (FP16 or FP32 compute and memory bandwidth). Updated with every build.

Local AI: what it runs

Model (Q4, 8K context)Tesla V100 SXM2 16 GB neededCosts nowSpeed (est.)
Llama 3.1 8B1 card$195.0093–139 tokens/s
Qwen3 14B1 card$195.0050–75 tokens/s
gpt-oss 20B1 card$195.00124–186 tokens/s
Gemma 3 27B2 cards$390.0027–41 tokens/s
Qwen3 32B2 cards$390.0023–34 tokens/s
Llama 3.3 70B4 cards$787.9811–16 tokens/s
gpt-oss 120B5 cards$987.9887–131 tokens/s
Qwen3 235B-A22Bmore than 8——
DeepSeek R1 / V3 671Bmore than 8——

Cost: that many of the cheapest live listings. Speed: an estimate from the memory bandwidth for one person chatting. Try other models, sizes and contexts.

Decision models

Model (Q4, 8K context)Tesla V100 SXM2 16 GB neededCosts nowPer question (est.)
Julia-10.144B1 card$195.005.9–13 ms
Laya0.421B1 card$195.009.9–21 ms
Kev-4B4B1 card$195.0024–51 ms
lev4B1 card$195.0071–152 ms
OpenJev27B2 cards$390.0085–182 ms
Clef27B2 cards$390.0085–182 ms
Perplexity Decider v1.227B2 cards$390.0085–182 ms
mammoth-127B2 cards$390.0085–182 ms

Decision models score the options you give them instead of writing text, so they're timed per question. The time is scaled from each model's reported speed on an RTX PRO 6000 by this card's compute and memory bandwidth, within about half either way. About the models.

Compare elsewhere

Search other shops for NVIDIA Tesla V100 SXM2 16 GB. These open the shop's own search; we don't show their prices here.