PerGB

NVIDIA Tesla V100 PCIe 32 GB

Live eBay prices, cheapest first. The best one right now is $975.00 (used).

Other sizes: 16 GB, 12 GB

Specs

VRAM
32 GB HBM2
Bandwidth
900 GB/s
FP32
14 TFLOPS
FP16
112 TFLOPS
Power
250 W
Connector
PCIe 3.0
Released
2017
Launch price
$10,000 (est.)
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.

Running it at home

Cooling
Passive: it has no fan. In a desktop it needs air pushed through it, front to back: a fan shroud on its end (3D-printed ones with a 40 mm blower or a 92 mm fan are sold for most of these cards) or a server chassis. Without one it overheats within minutes under load.
Power
One 8-pin CPU (EPS-12V) power input, not a PCIe one: it needs an adapter cable (two PCIe 8-pin to one EPS 8-pin, sold for these cards). A PCIe plug fits but is wired differently: never force one in. Rated 250 W: allow that for each card on top of the rest of the PC.
Size
Full height, two slots.
Motherboard
Turn on "Above 4G decoding" in the BIOS: without it many boards won't start with a card with this much memory.
Screen
No display outputs: use the processor's graphics or a small second card for a monitor.

A server card: made for a rack server's airflow and power. With these sorted it works in a normal PC.

Price right now

Live on eBay
Lowest now$975.00
Median ask$1,058
Per GB VRAM$30.47
vs launch price90% under
Live listings41

From the live listings below; shipping included.

Listings

Live on eBay
ListingConditionPriceChecked
Used$975.00−8%+$25.00 shipping
Used$975.00or best offer−8%free shipping
Used$979.00−7%free shipping
Used$980.00−7%free shipping
Used$985.52−7%+$100.00 shipping
Used$1,000or best offer−5%shipping not listed
Used$1,016or best offerfree shipping
Used$1,019or best offerfree shipping
Used$1,019or best offerfree shipping
Used$1,037free shipping
Used$1,040free shipping
Used$1,040free shipping
Used$1,040free shipping
Used$1,040free shipping
Used$1,040free shipping
Used$1,040free shipping
Used$1,045+$5.00 shipping
Used$1,049free shipping
Used$1,055+$5.00 shipping
Used$1,058or best offerfree shipping
Open box$1,058or best offerfree shipping
Open box$1,058or best offerfree shipping
Used$1,060or best offerfree shipping
Used$1,060free shipping
Used$1,099or best offerfree shipping
Used$1,120or best offerfree shipping
Used$1,134or best offer+$5.00 shipping
Used$1,144or best offerfree shipping
Used$1,150or best offerfree shipping
Used$1,150or best offerfree shipping
Used$1,150or best offerfree shipping
Used$1,185+$5.00 shipping
Used$1,189+$5.00 shipping
Used$1,200or best offerfree shipping
Used$1,201or best offerfree shipping
Refurbished$1,249free shipping
Refurbished$1,249free shipping
Used$1,250or best offerfree shipping
Used$1,298or best offerfree shipping
Used$1,400or best offerfree shipping
Used$1,457or best offerfree shipping

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

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 PCIe 32 GB neededCosts nowSpeed (est.)
Llama 3.1 8B1 card$975.0093–139 tokens/s
Qwen3 14B1 card$975.0050–75 tokens/s
gpt-oss 20B1 card$975.00124–186 tokens/s
Gemma 3 27B1 card$975.0027–41 tokens/s
Qwen3 32B1 card$975.0023–34 tokens/s
Llama 3.3 70B2 cards$1,95011–16 tokens/s
gpt-oss 120B3 cards$2,92987–131 tokens/s
Qwen3 235B-A22B5 cards$4,89520–30 tokens/s
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 PCIe 32 GB neededCosts nowPer question (est.)
Julia-10.144B1 card$975.006.3–13 ms
Laya0.421B1 card$975.0010–22 ms
Kev-4B4B1 card$975.0025–54 ms
lev4B1 card$975.0075–161 ms
OpenJev27B1 card$975.0090–192 ms
Clef27B1 card$975.0090–192 ms
Perplexity Decider v1.227B1 card$975.0090–192 ms
mammoth-127B1 card$975.0090–192 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 PCIe 32 GB. These open the shop's own search; we don't show their prices here.