NVIDIA Tesla V100 SXM3
Live eBay prices, cheapest first. The best one right now is $599.00 (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. SXM3 adapters are rare. The PCIe version: NVIDIA Tesla V100 PCIe 32 GB, from $975.00 → With its adapter board: NVIDIA Tesla V100 SXM3 mod kit, from $949.99 →
Other sizes: 16 GB
Specs
- VRAM
- 32 GB HBM2
- Bandwidth
- 1,134 GB/s
- FP32
- 16.4 TFLOPS
- FP16
- 130 TFLOPS
- Power
- 350 W
- Connector
- SXM3 (PCIe 3.0)
- Released
- 2018
- 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.
Price right now
Live on eBayFrom the live listings below; shipping included.
Listings
Live on eBay| Listing | Condition | Price | Checked |
|---|---|---|---|
| Used | $599.00or best offerfree shipping | ||
| Used | $699.00or best offerfree shipping | ||
| Used | $709.00or best offerfree shipping | ||
| Used | $824.00or best offerfree shipping | ||
| Open box | $1,699free shipping | ||
| Open box | $1,699free shipping | ||
| Open box | $1,699free shipping | ||
| Open box | $1,699free shipping | ||
| Open box | $1,785or best offerfree shipping | ||
| Used | $1,908or best offer+$38.88 shipping | ||
| Used | $2,057or best offer+$38.88 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 41 GPUs with 32 GB or more for the money: $402.18 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
- NVIDIA A100 SXM4 40 GB: $2,195, 270% of the GeForce RTX 3090, 40 GB
- AMD Instinct MI210: $3,799, 211% of the GeForce RTX 3090, 64 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 SXM3 needed | Costs now | Speed (est.) |
|---|---|---|---|
| Llama 3.1 8B | 1 card | $599.00 | 117–175 tokens/s |
| Qwen3 14B | 1 card | $599.00 | 63–95 tokens/s |
| gpt-oss 20B | 1 card | $599.00 | 156–234 tokens/s |
| Gemma 3 27B | 1 card | $599.00 | 34–51 tokens/s |
| Qwen3 32B | 1 card | $599.00 | 29–43 tokens/s |
| Llama 3.3 70B | 2 cards | $1,298 | 13–20 tokens/s |
| gpt-oss 120B | 3 cards | $2,007 | 110–165 tokens/s |
| Qwen3 235B-A22B | 5 cards | $4,530 | 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 V100 SXM3 needed | Costs now | Per question (est.) |
|---|---|---|---|
| Julia-10.144B | 1 card | $599.00 | 5.2–11 ms |
| Laya0.421B | 1 card | $599.00 | 8.6–18 ms |
| Kev-4B4B | 1 card | $599.00 | 21–44 ms |
| lev4B | 1 card | $599.00 | 62–133 ms |
| OpenJev27B | 1 card | $599.00 | 74–159 ms |
| Clef27B | 1 card | $599.00 | 74–159 ms |
| Perplexity Decider v1.227B | 1 card | $599.00 | 74–159 ms |
| mammoth-127B | 1 card | $599.00 | 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 V100 SXM3. These open the shop's own search; we don't show their prices here.









