NVIDIA Tesla V100 PCIe 12 GB
Live eBay prices, cheapest first. The best one right now is $261.00 (open box).
Specs
- VRAM
- 12 GB HBM2
- Bandwidth
- 900 GB/s
- FP32
- 14 TFLOPS
- FP16
- 112 TFLOPS
- Power
- 250 W
- Connector
- 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.
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 |
|---|---|---|---|
| Open box | $261.00or best offerfree shipping | ||
| Open box | $282.85or best offerfree shipping | ||
| Open box | $288.34+$29.99 shipping | ||
| Open box | $289.90or best offer+$5.00 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- #1 of 101 PCIe GPUs with 12 GB or more for the money: $211.92 per GeForce RTX 3090 of performance.
- Software: CUDA 9.0 to 12.9 (not CUDA 13).
Faster, for the least
- NVIDIA Tesla V100S PCIe: $1,099, 149% of the GeForce RTX 3090, 32 GB
- AMD Instinct MI100: $1,240, 185% of the GeForce RTX 3090, 32 GB
- NVIDIA GeForce RTX 4090: $2,094, 158% of the GeForce RTX 3090, 24 GB
More VRAM, for not much more
- NVIDIA Tesla P100 PCIe 16 GB: $170.00, 45% of the GeForce RTX 3090, 16 GB
- AMD Radeon VII: $249.00, 65% of the GeForce RTX 3090, 16 GB
- AMD Instinct MI50 16 GB: $266.00, 64% of the GeForce RTX 3090, 16 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 V100 PCIe 12 GB needed | Costs now | Speed (est.) |
|---|---|---|---|
| Llama 3.1 8B | 1 card | $261.00 | 93–139 tokens/s |
| Qwen3 14B | 1 card | $261.00 | 50–75 tokens/s |
| gpt-oss 20B | 2 cards | $543.85 | 124–186 tokens/s |
| Gemma 3 27B | 2 cards | $543.85 | 27–41 tokens/s |
| Qwen3 32B | 3 cards | $832.19 | 23–34 tokens/s |
| Llama 3.3 70B | 5 cards | not enough listings | 11–16 tokens/s |
| gpt-oss 120B | 7 cards | not enough listings | 87–131 tokens/s |
| Qwen3 235B-A22B | more than 8 | — | — |
| 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 V100 PCIe 12 GB needed | Costs now | Per question (est.) |
|---|---|---|---|
| Julia-10.144B | 1 card | $261.00 | 6.3–13 ms |
| Laya0.421B | 1 card | $261.00 | 10–22 ms |
| Kev-4B4B | 1 card | $261.00 | 25–54 ms |
| lev4B | 1 card | $261.00 | 75–161 ms |
| OpenJev27B | 2 cards | $543.85 | 90–192 ms |
| Clef27B | 2 cards | $543.85 | 90–192 ms |
| Perplexity Decider v1.227B | 2 cards | $543.85 | 90–192 ms |
| mammoth-127B | 2 cards | $543.85 | 90–192 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 12 GB. These open the shop's own search; we don't show their prices here.


