NVIDIA Tesla V100S PCIe
Live eBay prices, cheapest first. The best one right now is $1,099 (used).
Specs
- VRAM
- 32 GB HBM2
- Bandwidth
- 1,134 GB/s
- FP32
- 16.4 TFLOPS
- FP16
- 130 TFLOPS
- Power
- 250 W
- Connector
- PCIe 3.0
- Released
- 2019
- Launch price
- $10,000 (est.)
- CUDA compute
- 7.0
- Llama 3.1 8B at Q4 (est.)
- 117–175 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 eBayFrom the live listings below; shipping included.
Listings
Live on eBay| Listing | Condition | Price | Checked |
|---|---|---|---|
| Used | $1,099or best offer−27%free shipping | ||
| Used | $1,168or best offer−22%free shipping | ||
| Used | $1,169or best offer−22%free shipping | ||
| Used | $1,170or best offer−22%free shipping | ||
| Used | $1,198−20%free shipping | ||
| Used | $1,289or best offer−14%free shipping | ||
| Used | $1,484or best offerfree shipping | ||
| Open box | $1,499or best offerfree shipping | ||
| Open box | $1,499or best offerfree shipping | ||
| Open box | $1,663or best offerfree shipping | ||
| Open box | $1,685free shipping | ||
| Open box | $1,698or best offerfree shipping | ||
| Open box | $2,985free shipping | ||
| Open box | $4,165free shipping | ||
| Open box | $4,200free 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- #2 of 33 PCIe GPUs with 32 GB or more for the money: $737.88 per GeForce RTX 3090 of performance.
- Software: CUDA 9.0 to 12.9 (not CUDA 13).
Faster, for the least
- AMD Instinct MI100: $1,240, 185% of the GeForce RTX 3090, 32 GB
- AMD Instinct MI210: $3,799, 211% of the GeForce RTX 3090, 64 GB
- NVIDIA RTX PRO 4500 Blackwell: $4,399, 172% of the GeForce RTX 3090, 32 GB
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 V100S PCIe needed | Costs now | Speed (est.) |
|---|---|---|---|
| Llama 3.1 8B | 1 card | $1,099 | 117–175 tokens/s |
| Qwen3 14B | 1 card | $1,099 | 63–95 tokens/s |
| gpt-oss 20B | 1 card | $1,099 | 156–234 tokens/s |
| Gemma 3 27B | 1 card | $1,099 | 34–51 tokens/s |
| Qwen3 32B | 1 card | $1,099 | 29–43 tokens/s |
| Llama 3.3 70B | 2 cards | $2,267 | 13–20 tokens/s |
| gpt-oss 120B | 3 cards | $3,436 | 110–165 tokens/s |
| Qwen3 235B-A22B | 5 cards | $5,804 | 26–38 tokens/s |
| DeepSeek R1 / V3 671B | more 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 V100S PCIe needed | Costs now | Per question (est.) |
|---|---|---|---|
| Julia-10.144B | 1 card | $1,099 | 5.2–11 ms |
| Laya0.421B | 1 card | $1,099 | 8.6–18 ms |
| Kev-4B4B | 1 card | $1,099 | 21–44 ms |
| lev4B | 1 card | $1,099 | 62–133 ms |
| OpenJev27B | 1 card | $1,099 | 74–159 ms |
| Clef27B | 1 card | $1,099 | 74–159 ms |
| Perplexity Decider v1.227B | 1 card | $1,099 | 74–159 ms |
| mammoth-127B | 1 card | $1,099 | 74–159 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 V100S PCIe. These open the shop's own search; we don't show their prices here.












