GPU model · price + stock · hourly snapshot

Nvidia V100 cloud rental prices

2 providers list the Nvidia V100, 2 have it in stock. Prices run from $0.29 to $2.34 per GPU hour — the same card, 8.1x apart.

Volta 32 GB VRAM Q2 2017 21 configurations

LIVE Prices and stock checked 1 minute ago

Cheapest in stock
$0.29
Median
$1.31
across 2 providers
Most expensive
$2.34
same card, 8.1x the price
You overpay by
78%
if you take the median instead of the floor

Providers

Every provider renting the Nvidia V100

All providers →
Providers renting the Nvidia V100, in stock first, then cheapest first
Provider Country Configs Scale From Stock Days in stock Grab
CloudRift United States of America 12 5x-16x $0.29 In stock 11/14 Grab
Paperspace United States of America 9 1x-4x $2.34 In stock 60/60 Grab

In stock first, then cheapest. Stock is what the provider reported at our last check. One GPU for a month (730h) at $0.29: $212.

Price history

Price trend

Cheapest Nvidia V100 rate has fallen 88.1% since Sep 6 — $2.34 → $0.28/GPU/hr.

$0.278 /GPU/hr · Nov 4

One point per day: the lowest listed $/GPU/hr across every provider we track, captured daily. 338 offers in the latest snapshot.

Configurations

All 21 configurations

21 of 21 configurations
Nvidia V100 configurations from every provider
ConfigurationProviderRegionVRAMvCPURAMPer GPU/hrTotal/hrStock
5x V100 SXM3CloudRiftCloudRiftustx1a_a01160 GB50425 GB$0.29$1.45In stock
6x V100 SXM3CloudRiftCloudRiftustx1a_a01192 GB60510 GB$0.29$1.74In stock
7x V100 SXM3CloudRiftCloudRiftustx1a_a01224 GB70595 GB$0.29$2.03In stock
8x V100 SXM3CloudRiftCloudRiftustx1a_a01256 GB80680 GB$0.29$2.32In stock
9x V100 SXM3CloudRiftCloudRiftustx1a_a01288 GB90765 GB$0.29$2.61In stock
10x V100 SXM3CloudRiftCloudRiftustx1a_a01320 GB100850 GB$0.29$2.90In stock
11x V100 SXM3CloudRiftCloudRiftustx1a_a01352 GB110935 GB$0.29$3.19In stock
1x V100_32GPaperspacePaperspacenewyork-usa-132 GB830 GB$2.34$2.34In stock
4x V100_32GPaperspacePaperspacenewyork-usa-1128 GB32120 GB$2.34$9.36In stock
2x V100_32GPaperspacePaperspacenewyork-usa-164 GB1660 GB$2.34$4.68In stock
13x V100 SXM3CloudRiftCloudRiftustx1a_a01416 GB1301105 GB$0.29$3.77Out of stock
14x V100 SXM3CloudRiftCloudRiftustx1a_a01448 GB1401190 GB$0.29$4.06Out of stock
15x V100 SXM3CloudRiftCloudRiftustx1a_a01480 GB1501275 GB$0.29$4.35Out of stock
16x V100 SXM3CloudRiftCloudRiftustx1a_a01512 GB1601360 GB$0.29$4.64Out of stock
12x V100 SXM3CloudRiftCloudRiftustx1a_a01384 GB1201020 GB$0.29$3.48Out of stock
1x V100_32GPaperspacePaperspaceamsterdam-netherlands-132 GB830 GB$2.34$2.34Out of stock
1x V100_32GPaperspacePaperspacesantaclara-usa-132 GB830 GB$2.34$2.34Out of stock
4x V100_32GPaperspacePaperspaceamsterdam-netherlands-1128 GB32120 GB$2.34$9.36Out of stock
4x V100_32GPaperspacePaperspacesantaclara-usa-1128 GB32120 GB$2.34$9.36Out of stock
2x V100_32GPaperspacePaperspaceamsterdam-netherlands-164 GB1660 GB$2.34$4.68Out of stock
2x V100_32GPaperspacePaperspacesantaclara-usa-164 GB1660 GB$2.34$4.68Out of stock

Model fit

What fits in 32 GB

The question behind most rentals: will the model load. Sized against one Nvidia V100.

VRAM required to serve open-weight LLMs on a Nvidia V100, by quantization precision
Model 16-bit8-bit4-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.

Specifications

Nvidia V100 specifications

Nvidia V100 hardware specifications
ArchitectureVolta
Memory per GPU32 GB HBM2
Memory bandwidth900 GB/s
Release dateQ2 2017
GPU interconnectNVLink 300 GB/s
FP16 / BF16 compute rate125 TFLOPS (dense)
Process nodeTSMC 12nm FFN
Board power300 W

Alternatives

Alternatives to the Nvidia V100