Nvidia V100 cloud rental prices
5 providers list the Nvidia V100, 2 have it in stock. Prices run from $0.17 to $2.34 per GPU hour — the same card, 13.8x apart.
Prices and stock checked 2 hours ago
What it costs you to run
Estimated at the cheapest listed rate of $0.19/GPU/hr (Runpod), per GPU, before storage, egress or commitment discounts.
Renting at the median instead of the floor costs you an extra $161 a month per GPU. That is 56% of the bill, for identical silicon.
Every provider renting the Nvidia V100
Ordered strictly by entry price per GPU hour. Rows above the median are marked. Stock is what the provider reported at our last check, not a guarantee.
| Provider | Country | Configs | Scale | From | Spot | Reserved | Stock | Grab |
|---|---|---|---|---|---|---|---|---|
| Lium | — | 1 | 1x-1x | $0.17 | — | — | Out of stock | GrabLium — opens the provider's site |
| Runpod | United States of America | 4 | 1x-1x | $0.19 | $0.19 | — | In stock | GrabRunpod — opens the provider's site |
| Verda | Finland | 4 | 1x-8x | $0.39 | — | — | Out of stock | GrabVerda — opens the provider's site |
| Lambda Labs | United States of America | 7 | 8x-8x | $0.79 | — | — | Out of stock | GrabLambda Labs — opens the provider's site |
| Paperspace | United States of America | 12 | 1x-4x | $2.34 | — | — | In stock | GrabPaperspace — opens the provider's site |
Live inventory signal
The Lium marketplace publishes GPU counts, which almost nobody else does. It holds 0 Nvidia V100 GPUs at $0.17/GPU/hr, with 0% already rented. There is slack at that price today.
All 28 configurations
| Configuration | Provider | Region | VRAM | vCPU | RAM | Billing | Per GPU/hr | Total/hr | Stock |
|---|---|---|---|---|---|---|---|---|---|
| 1x NVIDIA Tesla V100 Tensor Core GPU | Lium | — | — | — | — | On-Demand | $0.17 | $0.17 | Out of stock |
| 1x Tesla V100 | Runpod | — | 16 GB | — | — | On-Demand | $0.19 | $0.19 | In stock |
| 1x Tesla V100 | Runpod | — | 16 GB | — | — | Spot | $0.19 | $0.19 | In stock |
| 1x V100 SXM2 | Runpod | — | 16 GB | — | — | On-Demand | $0.23 | $0.23 | In stock |
| 1x V100 SXM2 | Runpod | — | 16 GB | — | — | Spot | $0.23 | $0.23 | In stock |
| 2x V100 | Verda | helsinki-finland-1 | 32 GB | 10 | 45 GB | On-Demand | $0.39 | $0.78 | Out of stock |
| 8x V100 | Verda | helsinki-finland-2 | 128 GB | 48 | 180 GB | On-Demand | $0.39 | $3.12 | Out of stock |
| 4x V100 | Verda | helsinki-finland-1 | 64 GB | 20 | 90 GB | On-Demand | $0.39 | $1.56 | Out of stock |
| 1x V100 | Verda | helsinki-finland-1 | 16 GB | 6 | 23 GB | On-Demand | $0.39 | $0.39 | Out of stock |
| 8x V100 | Lambda Labs | mumbai-india-1 | 128 GB | 92 | 448 GB | On-Demand | $0.79 | $6.32 | Out of stock |
| 8x V100 | Lambda Labs | chicago-usa-2 | 128 GB | 92 | 448 GB | On-Demand | $0.79 | $6.32 | Out of stock |
| 8x V100 | Lambda Labs | phoenix-usa-2 | 128 GB | 92 | 448 GB | On-Demand | $0.79 | $6.32 | Out of stock |
| 8x V100 | Lambda Labs | sanjose-usa-2 | 128 GB | 92 | 448 GB | On-Demand | $0.79 | $6.32 | Out of stock |
| 8x V100 | Lambda Labs | dulles-usa-1 | 128 GB | 92 | 448 GB | On-Demand | $0.79 | $6.32 | Out of stock |
| 8x V100 | Lambda Labs | saltlakecity-usa-1 | 128 GB | 92 | 448 GB | On-Demand | $0.79 | $6.32 | Out of stock |
| 8x V100 | Lambda Labs | dallas-usa-2 | 128 GB | 92 | 448 GB | On-Demand | $0.79 | $6.32 | Out of stock |
| 1x V100_32G | Paperspace | amsterdam-netherlands-1 | 32 GB | 8 | 30 GB | On-Demand | $2.34 | $2.34 | Out of stock |
| 1x V100_32G | Paperspace | santaclara-usa-1 | 32 GB | 8 | 30 GB | On-Demand | $2.34 | $2.34 | Out of stock |
| 1x V100_32G | Paperspace | newyork-usa-1 | 32 GB | 8 | 30 GB | On-Demand | $2.34 | $2.34 | In stock |
| 4x V100_32G | Paperspace | amsterdam-netherlands-1 | 128 GB | 32 | 120 GB | On-Demand | $2.34 | $9.36 | Out of stock |
| 4x V100_32G | Paperspace | santaclara-usa-1 | 128 GB | 32 | 120 GB | On-Demand | $2.34 | $9.36 | Out of stock |
| 4x V100_32G | Paperspace | newyork-usa-1 | 128 GB | 32 | 120 GB | On-Demand | $2.34 | $9.36 | In stock |
| 2x V100_32G | Paperspace | amsterdam-netherlands-1 | 64 GB | 16 | 60 GB | On-Demand | $2.34 | $4.68 | Out of stock |
| 2x V100_32G | Paperspace | santaclara-usa-1 | 64 GB | 16 | 60 GB | On-Demand | $2.34 | $4.68 | Out of stock |
| 2x V100_32G | Paperspace | newyork-usa-1 | 64 GB | 16 | 60 GB | On-Demand | $2.34 | $4.68 | In stock |
| 1x V100 | Paperspace | amsterdam-netherlands-1 | 16 GB | 8 | 30 GB | On-Demand | $2.34 | $2.34 | Out of stock |
| 1x V100 | Paperspace | newyork-usa-1 | 16 GB | 8 | 30 GB | On-Demand | $2.34 | $2.34 | In stock |
| 1x V100 | Paperspace | santaclara-usa-1 | 16 GB | 8 | 30 GB | On-Demand | $2.34 | $2.34 | Out of stock |
What fits in 32 GB
The question behind most rentals: will the model load. Sized against one Nvidia V100.
| Model | 16-bit | 8-bit | 4-bit |
|---|---|---|---|
| DeepSeek-V3 DeepSeek · 671B params · 37B active | 1,610 GB 51× · 22 GB free | 805 GB 26× · 27 GB free | 403 GB 13× · 13 GB free |
| Llama 3.1 405B Meta · 405B params | 972 GB 31× · 20 GB free | 486 GB 16× · 26 GB free | 243 GB 8× · 13 GB free |
| Qwen3 235B-A22B Alibaba · 235B params · 22B active | 564 GB 18× · 12 GB free | 282 GB 9× · 6 GB free | 141 GB 5× · 19 GB free |
| Mixtral 8x22B Mistral · 141B params · 39B active | 338 GB 11× · 14 GB free | 169 GB 6× · 23 GB free | 85 GB 3× · 11 GB free |
| Mistral Large 2 Mistral · 123B params | 295 GB 10× · 25 GB free | 148 GB 5× · 12 GB free | 74 GB 3× · 22 GB free |
| gpt-oss-120b OpenAI · 117B params · 5.1B active | 281 GB 9× · 7 GB free | 140 GB 5× · 20 GB free | 70 GB 3× · 26 GB free |
| Qwen2.5 72B Alibaba · 72.7B params | 174 GB 6× · 18 GB free | 87 GB 3× · 9 GB free | 44 GB 2× · 20 GB free |
| Llama 3.3 70B Meta · 70.6B params | 169 GB 6× · 23 GB free | 85 GB 3× · 11 GB free | 42 GB 2× · 22 GB free |
| Qwen3 32B Alibaba · 32.8B params | 79 GB 3× · 17 GB free | 39 GB 2× · 25 GB free | 20 GB 1× · 12 GB free |
| Gemma 2 27B Google · 27.2B params | 65 GB 3× · 31 GB free | 33 GB 2× · 31 GB free | 16 GB 1× · 16 GB free |
| Mistral Small 3 Mistral · 24B params | 58 GB 2× · 6 GB free | 29 GB 1× · 3 GB free | 14 GB 1× · 18 GB free |
| Llama 3.1 8B Meta · 8B params | 19 GB 1× · 13 GB free | 10 GB 1× · 22 GB free | 5 GB 1× · 27 GB free |
Required memory is weights plus 20% for KV cache and runtime at short context; long contexts and large batches need more. Cells tinted green fit on a single Nvidia V100.
Nvidia V100 specifications
| Architecture | Volta |
|---|---|
| Memory per GPU | 32 GB HBM2 |
| Memory bandwidth | 900 GB/s |
| Release date | Q2 2017 |
| GPU interconnect | NVLink 300 GB/s |
| FP16 / BF16 compute rate | 125 TFLOPS (dense) |
| Process node | TSMC 12nm FFN |
| Board power | 300 W |
Frequently asked questions
How much does it cost to rent a Nvidia V100 per hour?
As of September 6, 2026 the Nvidia V100 rents from $0.17 per GPU per hour at Lium. The median across 5 providers is $0.39 and the dearest listing asks $2.34.
Who is the cheapest Nvidia V100 provider right now?
Lium at $0.17 per GPU per hour. That is 56% under the median of $0.39, so renting from a mid-priced provider costs you $0.22 an hour more for the same silicon.
What does a Nvidia V100 cost per month?
At the cheapest listed rate of $0.17 per GPU per hour, one Nvidia V100 running non-stop for a 730-hour month costs $124. At the median rate it costs $285.
Can I actually get a Nvidia V100 today?
Yes. 2 of 5 providers reported Nvidia V100 stock at the last check. The cheapest one with confirmed stock is Runpod at $0.19 per GPU per hour.
How much VRAM does the Nvidia V100 have?
32 GB HBM2 per board. That holds a model of roughly 12 billion parameters at 16-bit, or about 25 billion at 8-bit, before context and activations.
What architecture is the Nvidia V100, and when did it launch?
Volta, released Q2 2017. 5 cloud providers publish a price for it.