Data center GPU for combined AI inference and visualization.
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 L40 has 48 GB of VRAM. In practice, that's enough memory for roughly 68B parameters at 4-bit or 17B 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) | L40s needed | Cost /hr | Cost /mo |
|---|---|---|---|---|
Qwen3.8-27B
27B
|
18 GB
|
1
|
$1.06
|
$763
|
Gemma 4 31B
30.7B
|
22 GB
|
1
|
$1.06
|
$763
|
GPT-OSS-120B
117B · 5.1B active
|
67 GB
|
2
|
$2.12
|
$1,526
|
GLM-5.3-Flash
320B · 18B active
|
178 GB
|
8
|
$8.48
|
$6,106
|
MiniMax-M3
428B · 23B active
|
239 GB
|
8
|
$8.48
|
$6,106
|
DeepSeek V4.1 Flash
552B · 16B active
|
306 GB
|
8
|
$8.48
|
$6,106
|
Kimi K3
2.8T · 104B active
|
1,544 GB
|
36
|
–
|
–
|
Estimates based on the median on-demand rate. Memory is weights plus FP8 KV cache at 32K context per request (FP16/BF16 in the 16-bit column). 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 L40 · Per GPU
| Compute · dense | |
|---|---|
| FP8 | 362 TFLOPS 724 with sparsity |
| FP16 / BF16 | 181.1 TFLOPS 362.1 with sparsity |
| INT8 | 362 TOPS 724 with sparsity |
| FP32 | 90.5 TFLOPS |
| Precision support | FP8FP16BF16TF32FP32INT4INT8 |
| Memory | |
|---|---|
| Capacity | 48 GB GDDR6 |
| Bandwidth | 864 GB/s |
| Bus width | 384-bit |
| ECC | Yes |
| Silicon | |
|---|---|
| Architecture | Ada Lovelace |
| Process | TSMC 4N |
| Transistors | 76.3 billion |
| Shader cores | 18,176 CUDA cores |
| Matrix cores | 568 Tensor cores |
| Compute units | 142 SMs |
| Fabric and host | |
|---|---|
| Host interface | PCIe 4.0 x16 |
| Power | |
|---|---|
| Board power | 300 W |
| Cooling | Passive |
Source: official Nvidia L40 datasheet.
As of October 23, 2026, the median on-demand price is $1.06 per GPU per hour across 11 providers with a priced on-demand config.
| Billing type | Configs | Median /GPU/hr | Cheapest |
|---|---|---|---|
On-demand | 39 | $1.06 | $0.78 (in stock, GPU.ai) |
Reserved | 26 | $0.70 (not verified in stock, Hyperstack) |
|
Spot | 9 | $0.79 | $0.77 (in stock, Massed Compute) |
No median for reserved: we only show this when at least 3 providers list the GPU on that billing type.
The cheapest verified in-stock on-demand L40 tracked by GetDeploying is $0.78 per GPU per hour from GPU.ai. Other billing types: reserved $0.70 (not verified in stock) from Hyperstack and spot $0.77 (in stock) from Massed Compute.
At 720 hours per month, one L40 costs an estimated $763 at the median on-demand price. Cheapest verified in stock: $562 per month on-demand, $554 spot.
GetDeploying currently tracks L40 configs from 12 providers. The cheapest verified in-stock on-demand configs come from GPU.ai, Thunder Compute, Massed Compute and Sesterce. See the full price comparison above for every provider and config.
As of October 23, 2026, the median on-demand price has risen about 7% over the past 90 days to $1.06 per GPU per hour, though it is about 5% below where it was a year ago.
One L40 runs models up to roughly 68B parameters at 4-bit quantization or 17B 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.
48GB GDDR6 with Ada Lovelace architecture. Good for visualization, rendering, and inference workloads. FP8 Tensor Core support for efficient AI inference.
Last updated
