Nvidia L40
Data center GPU for combined AI inference and visualization.
- Arch
- Ada Lovelace
- Memory
- 48 GB GDDR6
- Bandwidth
- 864 GB/s
- Released
- Q4 2022
Price history
Weekly median price per GPU per hour
Aggregating historical prices...
At a glance Updated 12 minutes ago
- Cheapest in stock
- $0.33 /GPU/hr
- on-demand · 1x PCIe · Lium
- Median price (current)
- $0.98 /GPU/hr
- on-demand
- 90-day trend
- −5%
- median on-demand
- Coverage
- 14 providers
- 81 price points
Pricing & availability
How this list works
The two views
By provider shows one card per company, placed where its best offer ranked. By configuration lists every offer.
Order
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:
- Location: datacenter proximity, blended with provider HQ.
- Price: hourly price, per GPU and in total.
- Billing type: reserved ahead of spot, spot ahead of quote-only.
- Specs: more VRAM, vCPUs and RAM.
- Provider diversity: a provider's repeat rows rank slightly lower, so one company can't take all the top spots.
Search
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.
Transparency and funding
- Ads and sponsors: Paid placements sit at the top of the list and are always labeled as sponsored content. Sponsorship never influences the organic ranking itself.
- Affiliates: Affiliate links are marked. We may earn a commission if you click them, but commissions never affect the order.
- Prices: Shown in USD, converted at daily reference rates where a provider publishes in another currency. A month means 720 hours. How we estimate costs.
Runpod
In stock
USA
5 configs
1x-8x
EmpirioLabs AI
In stock
USA
4 configs
1x-8x
Massed Compute
In stock
USA
6 configs
1x-4x
Runcrate
In stock
USA
1 config
1x
Thunder Compute
In stock
USA
4 configs
1x-8x
Oblivus
In stock
USA
28 configs
1x-8x
Sesterce
In stock
France
8 configs
1x-8x
Vast.ai
In stock
USA
4 configs
1x-2x
GPU.ai
In stock
UAE
4 configs
1x-8x
Spheron
In stock
Singapore
9 configs
1x-8x
UK
3 configs
1x
USA
2 configs
8x
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.
What can the L40 run?
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.
Fits on 1
Single node ≤ 8
Multi-node
| Model | Memory (INT4 / FP4) | L40s needed | Cost /hr | Cost /mo |
|---|---|---|---|---|
Qwen3.8-27B
27B
|
18 GB
|
1
|
$0.98
|
$706
|
Gemma 4 31B
30.7B
|
22 GB
|
1
|
$0.98
|
$706
|
GPT-OSS-120B
117B · 5.1B active
|
67 GB
|
2
|
$1.96
|
$1,411
|
GLM-5.3-Flash
320B · 18B active
|
178 GB
|
8
|
$7.84
|
$5,645
|
MiniMax-M3
428B · 23B active
|
239 GB
|
8
|
$7.84
|
$5,645
|
DeepSeek V4.1 Flash
552B · 16B active
|
306 GB
|
8
|
$7.84
|
$5,645
|
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. How we estimate costs.
Technical Specifications
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.
Frequently Asked Questions
How much does the L40 cost per hour?
-
As of September 13, 2026, the median on-demand price is $0.98 per GPU per hour across 14 providers.
Billing type Configs Median /GPU/hr Cheapest On-demand
45
$0.98
$0.33 (in stock, Lium)
Reserved
26
$0.70
Spot
10
$0.78
$0.40 (in stock, Vast.ai)
No median for reserved: we only show this when at least 3 providers list the GPU on that billing type.
Who has the cheapest L40?
How much does the L40 cost per month?
-
At 720 hours per month, one L40 costs an estimated $706 at the median on-demand price. Cheapest verified in stock: $238 per month on-demand, $288 spot.
Where can I rent an L40?
-
GetDeploying currently tracks L40 configs from 14 providers. The cheapest verified in-stock on-demand configs come from Lium, Vast.ai, Runpod and EmpirioLabs AI. See the full price comparison above for every provider and config.
Are L40 prices going up or down?
-
As of September 13, 2026, the median on-demand price has fallen about 5% over the past 90 days to $0.98 per GPU per hour, and about 8% over the past 12 months.
How many L40 GPUs do I need?
-
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.
Why choose the L40?
-
48GB GDDR6 with Ada Lovelace architecture. Good for visualization, rendering, and inference workloads. FP8 Tensor Core support for efficient AI inference.
Alternatives to Nvidia L40
Last updated