Skip to main content
Hugging Face logo

L40S pricing on Hugging Face

Every Hugging Face L40S offering we track, normalized to a per-GPU hourly rate and ranked against 38 providers with current L40S pricing.

From / GPU-hr
$1.80
Price rank
#32 of 38
Configurations
3
Last updated
September 28, 2026

The cheapest L40S we currently track is $0.550/hr on Novita AI.

Hugging Face L40S rates

Hourly prices per GPU. Multi-GPU rows show the per-GPU rate, not the instance total.

Hugging Face L40S pricing by configuration
Price / GPU-hrTypeGPUs
$1.80On-demand1
$2.08On-demand4
$2.94On-demand8

L40S specifications

VRAM
48GB
Architecture
Ada Lovelace
CUDA Cores
18,176
Tensor Cores
568
Memory Bandwidth
864 GB/s
TDP
350W
Full L40S specs and every provider →

L40S on other providers

About Hugging Face

Hugging Face runs the Hub for open models and datasets. Inference Endpoints deploys a model on dedicated GPUs on AWS or Google Cloud, billed per hour of instance time, and Inference Providers routes API requests to partner inference providers at those providers' own rates.

Frequently Asked Questions

How much does the L40S cost on Hugging Face?

Hugging Face lists the L40S from $1.80 per GPU-hour across 3 tracked configurations. Prices are collected daily — see the table above for the current rates.

Is Hugging Face the cheapest place to rent the L40S?

Hugging Face ranks #32 of 38 providers we track with current L40S pricing. The cheapest right now is Novita AI. Price is only one factor — region availability, network, and storage costs differ between providers.

Which L40S configurations does Hugging Face offer?

We currently track 3 L40S offerings from Hugging Face, covering the GPU counts, pricing types, and regions listed in the table above. Every price is normalized to a per-GPU hourly rate so it can be compared across providers.