Nvidia L4
Low-power inference accelerator for cost-sensitive cloud deployments.
Compare vs other GPUs →Key Specifications
Compare Cloud Provider Prices
Barriers to entry are low here. 14 cloud providers list the L4 with prices starting at just $0.13/hr per GPU (spot instance), making it accessible for testing without a large commitment.
How we sort results
Default ranking
Our algorithm weighs five factors to find the most relevant matches for you:
- Price: We blend total hourly price with price-per-GPU to balance affordability and value.
- Specs: We favor offers with higher CPU, RAM, and GPU Memory.
- Billing: We favor on-demand billing for simplicity and flexibility over spot instances, reservations, and custom quotes.
- Location: We blend both datacenter proximity and provider HQ location. Datacenter location matters for latency, while HQ location matters for compliance and support.
- Provider diversity: Each time a provider appears in the list, their subsequent offerings are ranked a little lower, so one provider's offerings don't crowd out the top positions.
Sorting and filtering
Click any column header to sort by that column. Use the filters above the table to narrow results by billing type, GPU count, vCPUs, or RAM. Custom sorting resets the default relevance ranking.
Transparency and funding
Ads and sponsors: Any paid placements are fixed at the top and clearly labeled as sponsored content.
Affiliates: Any affiliate links will be indicated to you as well. We may earn a commission if you click them, but this never influences the ranking order.
| Provider | GPUs | Total VRAM | vCPUs | RAM | Billing | $/GPU/h | Total/h | Availability | |
|---|---|---|---|---|---|---|---|---|---|
Vast.ai
Our sponsor
|
1x L4 1x L4 23GB (35999126) | 23GB | 128 | 25GB | On-Demand Pay-as-you-go pricing. No term commitments. | $0.31 | $0.31 | Available | View |
Google Cloud
|
1x L4 1x L4 24GB (g2-standard-4) | 24GB | 4 | 16GB | On-Demand Pay-as-you-go pricing. No term commitments. | $0.71 | $0.71 | Available | View |
AWS
|
1x L4 1x L4 24GB (g6.xlarge) | 24GB | 4 | 16GB | On-Demand Pay-as-you-go pricing. No term commitments. | $2.30 | $2.30 | Available | View |
|
Google Cloud
|
1x L4 1x L4 24GB (g2-standard-8) | 24GB | 8 | 32GB | On-Demand Pay-as-you-go pricing. No term commitments. | $0.86 | $0.86 | Available | View |
UpCloud
|
1x L4 1x L4 24GB | 24GB | 8 | 64GB | On-Demand Pay-as-you-go pricing. No term commitments. | $0.66 | $0.66 | Unknown | View |
Koyeb
|
1x L4 1x L4 24GB (L4) | 24GB | 6 | 32GB | On-Demand Pay-as-you-go pricing. No term commitments. | $0.70 | $0.70 | Unknown | View |
Leaseweb
|
1x L4 1x L4 24GB (LSW.GR6.4XLARGE) | 24GB | 16 | 128GB | On-Demand Memory-optimized. | $0.85 | $0.85 | Unknown | View |
OVH
|
1x L4 1x L4 24GB (l4-90) | 24GB | 22 | 90GB | On-Demand Pay-as-you-go pricing. No term commitments. | $1.00 | $1.00 | Unknown | View |
Sesterce
|
1x L4 1x L4 24GB | 24GB | 8 | 48GB | On-Demand Pay-as-you-go pricing. No term commitments. | $1.04 | $1.04 | Available | View |
|
AWS
|
1x L4 1x L4 24GB (g6.8xlarge) | 24GB | 32 | 128GB | On-Demand Pay-as-you-go pricing. No term commitments. | $2.56 | $2.56 | Available | View |
|
Google Cloud
|
1x L4 1x L4 24GB (g2-standard-12) | 24GB | 12 | 48GB | On-Demand Pay-as-you-go pricing. No term commitments. | $1.01 | $1.01 | Available | View |
|
UpCloud
|
1x L4 1x L4 24GB | 24GB | 12 | 128GB | On-Demand Pay-as-you-go pricing. No term commitments. | $0.80 | $0.80 | Unknown | View |
|
Leaseweb
|
1x L4 1x L4 24GB (LSW.G6.XLARGE) | 24GB | 4 | 16GB | On-Demand Pay-as-you-go pricing. No term commitments. | $0.70 | $0.70 | Unknown | View |
Hexabyte
|
1x L4 1x L4 24GB | 24GB | 16 | 64GB | On-Demand Pay-as-you-go pricing. No term commitments. | $0.50 | $0.50 | Unknown | View |
Scaleway
|
1x L4 1x L4 24GB | 24GB | 8 | 48GB | On-Demand Pay-as-you-go pricing. No term commitments. | $0.90 | $0.90 | Unknown | View |
Elastx
|
1x L4 1x L4 24GB (g2-c6-m90-d800-g24) | 24GB | 6 | 90GB | On-Demand Pay-as-you-go pricing. No term commitments. | $0.94 | $0.94 | Unknown | View |
|
OVH
|
2x L4 2x L4 24GB (l4-180) | 48GB | 45 | 180GB | On-Demand Pay-as-you-go pricing. No term commitments. | $1.00 | $2.00 | Unknown | View |
|
Sesterce
|
2x L4 2x L4 24GB | 48GB | 16 | 96GB | On-Demand Pay-as-you-go pricing. No term commitments. | $1.04 | $2.09 | Available | View |
|
AWS
|
1x L4 1x L4 24GB (g6.2xlarge) | 24GB | 8 | 32GB | On-Demand Pay-as-you-go pricing. No term commitments. | $3.98 | $3.98 | Available | View |
|
Google Cloud
|
1x L4 1x L4 24GB (g2-standard-16) | 24GB | 16 | 64GB | On-Demand Pay-as-you-go pricing. No term commitments. | $1.16 | $1.16 | Available | View |
| No offerings matching your filters. | |||||||||
Heads up: We do our best to keep these specs & prices accurate. However, cloud costs may fluctuate based on region, usage, and other factors not listed here. These are estimates based on common setups and are for informational purposes only. Always verify current rates & exact specs with the provider before provisioning.
Frequently Asked Questions
Why choose the L4?
24GB GDDR6 in a low-power 72W form factor. FP8 support for efficient inference. Excellent performance-per-watt for deploying AI models at scale in cost-sensitive environments.
When is the L4 not a good fit?
Limited VRAM caps model sizes at ~13B parameters (FP16). Built for inference, not training. Low memory bandwidth (300 GB/s) may limit throughput on memory-bound workloads.
Are L4 prices going up or down?
On-demand pricing has increased by about 15% since June 2025, from $1.16 to $1.33/hr per GPU.
What size AI models can the L4 run?
With 24GB of VRAM, the L4 can typically run 7B to 13B models in FP16, or larger models in 4-bit quantized form.
How much VRAM does the L4 have?
The L4 has 24GB of VRAM. Multi-GPU setups increase total memory, but that memory is not automatically pooled across GPUs.
What is the L4's memory bandwidth?
The L4 has 300 GB/s of memory bandwidth. Higher bandwidth helps with faster data transfer between GPU memory and compute cores.
What data types does the L4 support?
The L4 supports 6 precision formats. Training: BF16, FP16, TF32, FP32. Inference: FP8, INT8.
Does the L4 support NVLink?
No. The L4 is a PCIe-only GPU with no NVLink, so it is better suited to single-GPU inference and smaller-scale workloads than large distributed training jobs.
How much does the L4 cost per hour?
L4 pricing currently ranges from $0.13/hr to $11.08/hr per GPU, depending on the provider, instance type, and billing model.
How much does the L4 cost per month?
At 720 hours per month, one L4 can cost between $96.52 to $7,975.30 per month, depending on the provider. Reserved and spot pricing can lower that further.
Which cloud providers offer the L4?
The L4 is available from 14 cloud providers, including Amazon Web Services, UpCloud, Leaseweb. Pricing and availability vary by region and billing model.
Can I rent the L4 in the cloud?
Yes. We currently track 110 L4 listings across 14 cloud providers:
Billing type Listings Avg $/GPU/hr On-demand 62 $1.36/hr Reserved 35 $2.17/hr Spot 13 $0.26/hr
Technical Specifications
| FP32 | 30.3 TFLOPs |
| TF32 Tensor Core | 120 TFLOPs |
| FP16 Tensor Core | 242 TFLOPs |
| BFLOAT16 Tensor Core | 242 TFLOPs |
| FP8 Tensor Core | 485 TFLOPs |
| INT8 Tensor Core | 485 TOPs |
| GPU Memory | 24GB |
| GPU Memory Bandwidth | 300 GB/s |
| NVENC, NVDEC, JPEG Decoders | 2, 4, 4 |
| Max Thermal Design Power (TDP) | 72W |
| Form Factor | 1-slot low-profile, PCIe |
| Interconnect | PCIe Gen4 x16 64GB/s |
| Server Options | Partner and NVIDIA-Certified Systems with 1‒8 GPUs |
Source: official Nvidia L4 datasheet.
Alternatives to Nvidia L4
Last updated