Legacy data center GPU with FP64 support for scientific computing.
Weekly median price per GPU per hour · Get the data
By provider shows one card per company, placed where its best offer ranked. By configuration lists every offer.
What you can rent comes first: in stock, then waitlist, then not reported, then out of stock. Priced offers rank ahead of quote-only, and on-demand ahead of other billing types.
Within a group, five factors set the order:
We match the provider, its country, GPU model, form factor, billing type, availability and instance name. Matching is partial and case-insensitive. Everyday words work too, so "interruptible" finds spot and "sold out" finds out of stock.
No providers match .
Heads up: A provider's own page may quote a different figure, for example on tax, region or a promotion. A monthly-only plan shows a derived hourly rate. Verify before provisioning. More on how we price.
One V100 has 32 GB of VRAM. In practice, that's enough memory for roughly 34B parameters at 4-bit or 9B at 16-bit, assuming a 32K context. Below are some open-weight LLMs, with the estimated memory and GPUs each one needs.
| Model | Memory (INT4 / FP4) | V100s needed | Cost /hr | Cost /mo |
|---|---|---|---|---|
Qwen3.8-27B
27B
|
19 GB
|
1
|
$1.57
|
$1,130
|
Gemma 4 31B
30.7B
|
24 GB
|
1
|
$1.57
|
$1,130
|
GPT-OSS-120B
117B · 5.1B active
|
68 GB
|
3
|
$4.71
|
$3,391
|
GLM-5.3-Flash
320B · 18B active
|
178 GB
|
8
|
$12.56
|
$9,043
|
MiniMax-M3
428B · 23B active
|
241 GB
|
9
|
–
|
–
|
DeepSeek V4.1 Flash
552B · 16B active
|
306 GB
|
11
|
–
|
–
|
Kimi K3
2.8T · 104B active
|
1,545 GB
|
54
|
–
|
–
|
Estimates based on the median on-demand rate. Memory is weights plus FP16/BF16 KV cache at 32K context per request. GPU counts assume 90% of advertised VRAM is usable. No guarantee of runtime support, usable performance, or that a matching quantized build exists. Pricing methodology.
Nvidia V100 · Per GPU
| Compute · dense | |
|---|---|
| FP16 / BF16 | 125 TFLOPS |
| FP32 | 15.7 TFLOPS |
| FP64 | 7.8 TFLOPS |
| Precision support | FP16FP32FP64INT8 |
| Memory | |
|---|---|
| Capacity | 32 GB HBM2 |
| Bandwidth | 900 GB/s |
| Bus width | 4,096-bit |
| ECC | Yes |
| Silicon | |
|---|---|
| Architecture | Volta |
| Process | TSMC 12nm FFN |
| Transistors | 21.1 billion |
| Shader cores | 5,120 CUDA cores |
| Matrix cores | 640 Tensor cores |
| Compute units | 80 SMs |
| Fabric and host | |
|---|---|
| GPU interconnect | NVLink 300 GB/s |
| Host interface | PCIe 3.0 |
| Power | |
|---|---|
| Board power | 300 W |
| Cooling | Passive |
Source: official Nvidia V100 datasheet.
At 720 hours per month, one V100 costs an estimated $1,130 at the median on-demand price. Cheapest verified in stock: $65 per month on-demand, $65 reserved (3 mo), $72 spot.
GetDeploying currently tracks V100 configs from 20 providers. The cheapest verified in-stock on-demand configs come from Vast.ai, HyperAI, Runcrate and Sesterce. See the full price comparison above for every provider and config.
As of September 28, 2026, the median on-demand price has fallen about 38% over the past 90 days to $1.57 per GPU per hour, though it is about 10% above where it was a year ago.
One V100 runs models up to roughly 34B parameters at 4-bit quantization or 9B at 16-bit, assuming a 32K context. Larger models run across multiple GPUs: the model table above shows the estimated memory and GPU count for popular open-weight LLMs.
32GB or 16GB HBM2 with 300 GB/s NVLink. Legacy data center GPU with wide availability and low cost. FP64 support makes it useful for scientific computing.
Volta architecture lacks BF16, TF32, and FP8 support. Significantly slower than Ampere or Hopper for AI workloads. Only consider if budget is the primary constraint.
Nvidia H100
80 GB HBM3 · 3.7x the bandwidth of the V100
Nvidia RTX 5090
32 GB GDDR7 · 99% more bandwidth than the V100
Nvidia A100
80 GB HBM2e · 2.1x the bandwidth of the V100
Nvidia RTX 4090
24 GB GDDR6X · PCIe only
Nvidia L40S
48 GB GDDR6 · PCIe only
Last updated
