NVIDIA Tesla V100 SXM2 32 GB
Live eBay prices, cheapest first. The best one right now is $799.00 (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 32 GB, from $975.00 → With its adapter board: NVIDIA Tesla V100 SXM2 32 GB mod kit, from $949.00 →
Other sizes: 16 GB
Specs
- VRAM
- 32 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 eBayFrom the live listings below; shipping included.
Listings
Live on eBay| Listing | Condition | Price | Checked |
|---|---|---|---|
| Used | $799.00or best offer−24%free shipping | ||
| Used | $799.00or best offer−24%free shipping | ||
| Used | $890.00−15%free shipping | ||
| Used | $899.90−14%free shipping | ||
| Used | $899.90−14%free shipping | ||
| Used | $900.00−14%free shipping | ||
| Used | $900.00−14%free shipping | ||
| Used | $903.00−14%+$5.00 shipping | ||
| Used | $945.80or best offer−10%free shipping | ||
| Used | $949.90−10%free shipping | ||
| Used | $958.18−9%+$2.95 shipping | ||
| Used | $960.97−8%+$2.97 shipping | ||
| Used | $961.97−8%+$2.97 shipping | ||
| Used | $1,025+$5.00 shipping | ||
| Used | $1,025+$5.00 shipping | ||
| Used | $1,030+$30.00 shipping | ||
| Used | $1,045or best offerfree shipping | ||
| Used | $1,045or best offerfree shipping | ||
| Used | $1,047free shipping | ||
| Used | $1,050or best offerfree shipping | ||
| Used | $1,057free shipping | ||
| Used | $1,058free shipping | ||
| Open box | $1,067+$210.00 shipping | ||
| Used | $1,070+$20.00 shipping | ||
| Used | $1,091+$7.00 shipping | ||
| Used | $1,097free shipping | ||
| Open box | $1,099+$50.00 shipping | ||
| Used | $1,099free shipping | ||
| Used | $1,100or best offerfree shipping | ||
| Open box | $1,150or best offerfree shipping | ||
| Used | $1,160+$60.00 shipping | ||
| Used | $1,250or best offerfree shipping | ||
| Used | $1,299or best offer+$5.00 shipping | ||
| Used | $1,385+$5.00 shipping | ||
| Used | $1,423free shipping | ||
| Used | $1,499free shipping | ||
| Used | $1,499free shipping | ||
| Used | $1,499free shipping | ||
| Used | $2,134free 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 41 GPUs with 32 GB or more for the money: $614.10 per GeForce RTX 3090 of performance.
- Software: CUDA 9.0 to 12.9 (not CUDA 13).
As much VRAM, about as fast, for less
- NVIDIA Tesla V100 SXM3: $599.00, 149% of the GeForce RTX 3090, 32 GB
Faster, for the least
- 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
- NVIDIA A100 SXM4 40 GB: $2,195, 270% of the GeForce RTX 3090, 40 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 SXM2 32 GB needed | Costs now | Speed (est.) |
|---|---|---|---|
| Llama 3.1 8B | 1 card | $799.00 | 93–139 tokens/s |
| Qwen3 14B | 1 card | $799.00 | 50–75 tokens/s |
| gpt-oss 20B | 1 card | $799.00 | 124–186 tokens/s |
| Gemma 3 27B | 1 card | $799.00 | 27–41 tokens/s |
| Qwen3 32B | 1 card | $799.00 | 23–34 tokens/s |
| Llama 3.3 70B | 2 cards | $1,598 | 11–16 tokens/s |
| gpt-oss 120B | 3 cards | $2,488 | 87–131 tokens/s |
| Qwen3 235B-A22B | 5 cards | $4,288 | 20–30 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 V100 SXM2 32 GB needed | Costs now | Per question (est.) |
|---|---|---|---|
| Julia-10.144B | 1 card | $799.00 | 5.9–13 ms |
| Laya0.421B | 1 card | $799.00 | 9.9–21 ms |
| Kev-4B4B | 1 card | $799.00 | 24–51 ms |
| lev4B | 1 card | $799.00 | 71–152 ms |
| OpenJev27B | 1 card | $799.00 | 85–182 ms |
| Clef27B | 1 card | $799.00 | 85–182 ms |
| Perplexity Decider v1.227B | 1 card | $799.00 | 85–182 ms |
| mammoth-127B | 1 card | $799.00 | 85–182 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 32 GB. These open the shop's own search; we don't show their prices here.





























