datacenter
租用 Nvidia L40S.
Ada Lovelace
48GB VRAM
From $0.53/hr
Per hour
$0.53
Per day
$12.72
Per week
$89.04
Per month
$382
Provider spread
12 providers ·
up to 72% cheaper at the low end
Cheapest · $0.53/hr on Lium
Median $0.92/hr
Most expensive · $1.87/hr on AceCloud
Price history
Daily median across providers.
Loading...
Where to rent it
All providers carrying this GPU.
Workloads
Suitable workloads.
AI models that fit
See all 32 →
Run these on this GPU.
- Qwen 2.5 72B 1× · int4
- Qwen2.5 72B Instruct 1× · int4
- DeepSeek R1 Distill Qwen 14B 1× · fp16
Cloud instances
See all 203 →
Hyperscaler bundles.
Pre-configured on 8 clouds — from $0.55/hr total
($0.55/hr per GPU).
FAQ
Frequently asked.
How much does it cost to rent the Nvidia L40S right now?
The cheapest current listing is $0.53/hr on Lium, and the median across the 12 providers listing it is $0.96/hr. Running one around the clock for a month (730 hours) at the cheapest rate costs about $387.
What AI models can the Nvidia L40S run?
With 48 GB it runs 70B models at 4-bit (about 35–40 GB of weights plus KV cache) and 32B models at INT8. It can QLoRA fine-tune models up to about 70B with short sequences, and 32B comfortably.
Which models are recommended for the Nvidia L40S?
32 models in our catalog have a recommended configuration for this card, with the quantization that fits its 48 GB — see the AI models tab.
Why does the Nvidia L40S cost different amounts on different providers?
Marketplaces such as Vast.ai and Clore.ai list machines from independent hosts who set their own prices, so competition pushes rates down but reliability varies by host. Operator clouds such as Lambda and the hyperscalers charge more for consistent hardware, support and networking. Prices here are per GPU, so they compare directly.
How is the Nvidia L40S price calculated?
We collect listings from each provider's public API or price page — every 5–10 minutes for marketplaces, up to daily for operator clouds — and show the median hourly price per provider from the last 24 hours, so one unusually cheap listing doesn't set the headline. Details are on the methodology page.
Cloud instance options
Pre-configured instances on hyperscalers.
Whole-instance bundles (GPU + vCPU + RAM + disk) on the major clouds. Per-GPU rate often drops as the count rises. View = spec page · Launch = sign up (affiliate).
Cheapest bundle
$0.55/hr
Lowest $/hr per GPU
$0.55/hr
Providers
8
Instance shapes
203
| Provider | Instance | GPUs | vCPU | RAM | Disk | $/hr | $/hr per GPU | |
|---|---|---|---|---|---|---|---|---|
| L40S.22c125g | 1× | 22 | 125 GB | — | $0.55/hr | $0.55/hr | ||
| L40S.22c125g | 1× | 22 | 125 GB | — | $0.55/hr | $0.55/hr | ||
| L40S.22c125g | 1× | 22 | 125 GB | — | $0.55/hr | $0.55/hr | ||
| L40S.22c125g | 1× | 22 | 125 GB | — | $0.55/hr | $0.55/hr | ||
| L40S.22c125g | 1× | 22 | 125 GB | — | $0.55/hr | $0.55/hr | ||
| L40S.22c125g | 1× | 22 | 125 GB | — | $0.55/hr | $0.55/hr | ||
| L40S.22c125g | 1× | 22 | 125 GB | — | $0.55/hr | $0.55/hr | ||
| L40S.22c125g | 1× | 22 | 125 GB | — | $0.55/hr | $0.55/hr | ||
| L40S.22c125g | 1× | 22 | 125 GB | — | $0.55/hr | $0.55/hr | ||
| L40S.22c125g | 1× | 22 | 125 GB | — | $0.55/hr | $0.55/hr | ||
| L40S.22c125g | 1× | 22 | 125 GB | — | $0.55/hr | $0.55/hr | ||
| L40S.22c125g | 1× | 22 | 125 GB | — | $0.55/hr | $0.55/hr | ||
| L40S.22c125g | 1× | 22 | 125 GB | — | $0.55/hr | $0.55/hr | ||
| L40S.22c125g | 1× | 22 | 125 GB | — | $0.55/hr | $0.55/hr | ||
| L40S.22c125g | 1× | 22 | 125 GB | — | $0.55/hr | $0.55/hr | ||
| L40S.22c125g | 1× | 22 | 125 GB | — | $0.55/hr | $0.55/hr | ||
| L40S.22c125g | 1× | 22 | 125 GB | — | $0.55/hr | $0.55/hr | ||
| L40S.22c125g | 1× | 22 | 125 GB | — | $0.55/hr | $0.55/hr | ||
| L40S.22c125g | 1× | 22 | 125 GB | — | $0.55/hr | $0.55/hr | ||
| no-kristiansand-1/epyc-genoa-l40s-graphics | 1× | 1 | 1 GB | — | $0.88/hr | $0.88/hr | ||
| no-kristiansand-1/epyc-genoa-l40s-graphics | 1× | 1 | 1 GB | — | $0.88/hr | $0.88/hr | ||
| no-kristiansand-1/epyc-genoa-l40s-graphics | 1× | 1 | 1 GB | — | $0.88/hr | $0.88/hr | ||
| no-kristiansand-1/epyc-genoa-l40s-graphics | 1× | 1 | 1 GB | — | $0.88/hr | $0.88/hr | ||
| no-kristiansand-1/epyc-genoa-l40s-graphics | 1× | 1 | 1 GB | — | $0.88/hr | $0.88/hr | ||
| no-kristiansand-1/epyc-genoa-l40s-graphics | 1× | 1 | 1 GB | — | $0.88/hr | $0.88/hr | ||
| no-kristiansand-1/epyc-genoa-l40s-graphics | 1× | 1 | 1 GB | — | $0.88/hr | $0.88/hr | ||
| no-kristiansand-1/epyc-genoa-l40s-graphics | 1× | 1 | 1 GB | — | $0.88/hr | $0.88/hr | ||
| no-kristiansand-1/epyc-genoa-l40s-graphics | 1× | 1 | 1 GB | — | $0.88/hr | $0.88/hr | ||
| no-kristiansand-1/epyc-genoa-l40s-graphics | 1× | 1 | 1 GB | — | $0.88/hr | $0.88/hr | ||
| no-kristiansand-1/epyc-genoa-l40s-graphics | 1× | 1 | 1 GB | — | $0.88/hr | $0.88/hr | ||
| no-kristiansand-1/epyc-genoa-l40s-graphics | 1× | 1 | 1 GB | — | $0.88/hr | $0.88/hr | ||
| no-kristiansand-1/epyc-genoa-l40s-graphics | 1× | 1 | 1 GB | — | $0.88/hr | $0.88/hr | ||
| no-kristiansand-1/epyc-genoa-l40s-graphics | 1× | 1 | 1 GB | — | $0.88/hr | $0.88/hr | ||
| no-kristiansand-1/epyc-genoa-l40s-graphics | 1× | 1 | 1 GB | — | $0.88/hr | $0.88/hr | ||
| no-kristiansand-1/epyc-genoa-l40s-graphics | 1× | 1 | 1 GB | — | $0.88/hr | $0.88/hr | ||
| no-kristiansand-1/epyc-genoa-l40s-graphics | 1× | 1 | 1 GB | — | $0.88/hr | $0.88/hr | ||
| no-kristiansand-1/epyc-genoa-l40s-graphics | 1× | 1 | 1 GB | — | $0.88/hr | $0.88/hr | ||
| no-kristiansand-1/epyc-genoa-l40s-graphics | 1× | 1 | 1 GB | — | $0.88/hr | $0.88/hr | ||
| no-kristiansand-1/epyc-genoa-l40s-graphics | 1× | 1 | 1 GB | — | $0.88/hr | $0.88/hr | ||
| 1x L40S_PCIE | 1× | 12 | 72 GB | 625 GB | $0.96/hr | $0.96/hr | ||
| 1x L40S_PCIE | 1× | 12 | 72 GB | 625 GB | $0.96/hr | $0.96/hr | ||
| 1x L40S_PCIE | 1× | 12 | 72 GB | 625 GB | $0.96/hr | $0.96/hr | ||
| 1x L40S_PCIE | 1× | 12 | 72 GB | 625 GB | $0.96/hr | $0.96/hr | ||
| 1x L40S_PCIE | 1× | 12 | 72 GB | 625 GB | $0.96/hr | $0.96/hr | ||
| 1x L40S_PCIE | 1× | 12 | 72 GB | 625 GB | $0.96/hr | $0.96/hr | ||
| 1x L40S_PCIE | 1× | 12 | 72 GB | 625 GB | $0.96/hr | $0.96/hr | ||
| 1x L40S_PCIE | 1× | 12 | 72 GB | 625 GB | $0.96/hr | $0.96/hr | ||
| 1x L40S_PCIE | 1× | 12 | 72 GB | 625 GB | $0.96/hr | $0.96/hr | ||
| 1x L40S_PCIE | 1× | 12 | 72 GB | 625 GB | $0.96/hr | $0.96/hr | ||
| 1x L40S_PCIE | 1× | 12 | 72 GB | 625 GB | $0.96/hr | $0.96/hr | ||
| 1x L40S_PCIE | 1× | 12 | 72 GB | 625 GB | $0.96/hr | $0.96/hr | ||
| 1x L40S_PCIE | 1× | 12 | 72 GB | 625 GB | $0.96/hr | $0.96/hr | ||
| 1x L40S_PCIE | 1× | 12 | 72 GB | 625 GB | $0.96/hr | $0.96/hr | ||
| 1x L40S_PCIE | 1× | 12 | 72 GB | 625 GB | $0.96/hr | $0.96/hr | ||
| 1x L40S_PCIE | 1× | 12 | 72 GB | 625 GB | $0.96/hr | $0.96/hr | ||
| 1x L40S_PCIE | 1× | 12 | 72 GB | 625 GB | $0.96/hr | $0.96/hr | ||
| L40S | 1× | 12 | 72 GB | 625 GB | $0.97/hr | $0.97/hr | ||
| L40S | 1× | 12 | 72 GB | 625 GB | $0.97/hr | $0.97/hr | ||
| L40S | 1× | 12 | 72 GB | 625 GB | $0.97/hr | $0.97/hr | ||
| L40S | 1× | 12 | 72 GB | 625 GB | $0.97/hr | $0.97/hr | ||
| L40S | 1× | 12 | 72 GB | 625 GB | $0.97/hr | $0.97/hr | ||
| L40S | 1× | 12 | 72 GB | 625 GB | $0.97/hr | $0.97/hr | ||
| L40S | 1× | 12 | 72 GB | 625 GB | $0.97/hr | $0.97/hr | ||
| L40S | 1× | 12 | 72 GB | 625 GB | $0.97/hr | $0.97/hr | ||
| L40S | 1× | 12 | 72 GB | 625 GB | $0.97/hr | $0.97/hr | ||
| L40S | 1× | 12 | 72 GB | 625 GB | $0.97/hr | $0.97/hr | ||
| L40S | 1× | 12 | 72 GB | 625 GB | $0.97/hr | $0.97/hr | ||
| L40S | 1× | 12 | 72 GB | 625 GB | $0.97/hr | $0.97/hr | ||
| L40S | 1× | 12 | 72 GB | 625 GB | $0.97/hr | $0.97/hr | ||
| L40S | 1× | 12 | 72 GB | 625 GB | $0.97/hr | $0.97/hr | ||
| L40S | 1× | 12 | 72 GB | 625 GB | $0.97/hr | $0.97/hr | ||
| L40S | 1× | 12 | 72 GB | 625 GB | $0.97/hr | $0.97/hr | ||
| 1L40S.16v.256m | 1× | 16 | 256 GB | — | $1.28/hr | $1.28/hr | ||
| 1L40S.16v.256m | 1× | 16 | 256 GB | — | $1.28/hr | $1.28/hr | ||
| 1L40S.16v.256m | 1× | 16 | 256 GB | — | $1.28/hr | $1.28/hr | ||
| g6e.xlarge | 1× | — | — | — | $1.86/hr | $1.86/hr | ||
| g6e.xlarge | 1× | — | — | — | $1.86/hr | $1.86/hr | ||
| g6e.xlarge | 1× | — | — | — | $1.86/hr | $1.86/hr | ||
| N.L40S.64 | 1× | 16 | 64 GB | — | $1.87/hr | $1.87/hr | ||
| N.L40S.64 | 1× | 16 | 64 GB | — | $1.87/hr | $1.87/hr | ||
| N.L40S.64 | 1× | 16 | 64 GB | — | $1.87/hr | $1.87/hr | ||
| L40S | 1× | 8 | 96 GB | 1000 GB | $1.87/hr | $1.87/hr | ||
| 1x L40S_PCIE | 1× | 8 | 32 GB | 512 GB | $2.11/hr | $2.11/hr | ||
| 1x L40S_PCIE | 1× | 8 | 32 GB | 512 GB | $2.11/hr | $2.11/hr | ||
| g6e.2xlarge | 1× | — | — | — | $2.24/hr | $2.24/hr | ||
| g6e.2xlarge | 1× | — | — | — | $2.24/hr | $2.24/hr | ||
| g6e.2xlarge | 1× | — | — | — | $2.24/hr | $2.24/hr | ||
| N.L40S.128 | 1× | 16 | 128 GB | — | $2.27/hr | $2.27/hr | ||
| N.L40S.128 | 1× | 16 | 128 GB | — | $2.27/hr | $2.27/hr | ||
| N.L40S.128 | 1× | 16 | 128 GB | — | $2.27/hr | $2.27/hr | ||
| g6e.4xlarge | 1× | — | — | — | $3.00/hr | $3.00/hr | ||
| g6e.4xlarge | 1× | — | — | — | $3.00/hr | $3.00/hr | ||
| g6e.4xlarge | 1× | — | — | — | $3.00/hr | $3.00/hr | ||
| g6e.8xlarge | 1× | — | — | — | $4.53/hr | $4.53/hr | ||
| g6e.8xlarge | 1× | — | — | — | $4.53/hr | $4.53/hr | ||
| g6e.8xlarge | 1× | — | — | — | $4.53/hr | $4.53/hr | ||
| g6e.16xlarge | 1× | — | — | — | $7.58/hr | $7.58/hr | ||
| g6e.16xlarge | 1× | — | — | — | $7.58/hr | $7.58/hr | ||
| g6e.16xlarge | 1× | — | — | — | $7.58/hr | $7.58/hr | ||
| 2x L40S_PCIE | 2× | 24 | 144 GB | 1250 GB | $1.92/hr | $0.96/hr | ||
| 2x L40S_PCIE | 2× | 24 | 144 GB | 1250 GB | $1.92/hr | $0.96/hr | ||
| 2x L40S_PCIE | 2× | 24 | 144 GB | 1250 GB | $1.92/hr | $0.96/hr | ||
| 2x L40S_PCIE | 2× | 24 | 144 GB | 1250 GB | $1.92/hr | $0.96/hr | ||
| 2x L40S_PCIE | 2× | 24 | 144 GB | 1250 GB | $1.92/hr | $0.96/hr | ||
| 2x L40S_PCIE | 2× | 24 | 144 GB | 1250 GB | $1.92/hr | $0.96/hr | ||
| 2x L40S_PCIE | 2× | 24 | 144 GB | 1250 GB | $1.92/hr | $0.96/hr | ||
| 2x L40S_PCIE | 2× | 24 | 144 GB | 1250 GB | $1.92/hr | $0.96/hr | ||
| 2x L40S_PCIE | 2× | 24 | 144 GB | 1250 GB | $1.92/hr | $0.96/hr | ||
| 2x L40S_PCIE | 2× | 24 | 144 GB | 1250 GB | $1.92/hr | $0.96/hr | ||
| 2x L40S_PCIE | 2× | 24 | 144 GB | 1250 GB | $1.92/hr | $0.96/hr | ||
| 2x L40S_PCIE | 2× | 24 | 144 GB | 1250 GB | $1.92/hr | $0.96/hr | ||
| 2x L40S_PCIE | 2× | 24 | 144 GB | 1250 GB | $1.92/hr | $0.96/hr | ||
| 2x L40S_PCIE | 2× | 24 | 144 GB | 1250 GB | $1.92/hr | $0.96/hr | ||
| 2x L40S_PCIE | 2× | 24 | 144 GB | 1250 GB | $1.92/hr | $0.96/hr | ||
| L40Sx2 | 2× | 44 | 256 GB | 1250 GB | $1.94/hr | $0.97/hr | ||
| L40Sx2 | 2× | 44 | 256 GB | 1250 GB | $1.94/hr | $0.97/hr | ||
| L40Sx2 | 2× | 44 | 256 GB | 1250 GB | $1.94/hr | $0.97/hr | ||
| L40Sx2 | 2× | 44 | 256 GB | 1250 GB | $1.94/hr | $0.97/hr | ||
| L40Sx2 | 2× | 44 | 256 GB | 1250 GB | $1.94/hr | $0.97/hr | ||
| L40Sx2 | 2× | 44 | 256 GB | 1250 GB | $1.94/hr | $0.97/hr | ||
| L40Sx2 | 2× | 44 | 256 GB | 1250 GB | $1.94/hr | $0.97/hr | ||
| L40Sx2 | 2× | 44 | 256 GB | 1250 GB | $1.94/hr | $0.97/hr | ||
| L40Sx2 | 2× | 44 | 256 GB | 1250 GB | $1.94/hr | $0.97/hr | ||
| L40Sx2 | 2× | 44 | 256 GB | 1250 GB | $1.94/hr | $0.97/hr | ||
| L40Sx2 | 2× | 44 | 256 GB | 1250 GB | $1.94/hr | $0.97/hr | ||
| L40Sx2 | 2× | 44 | 256 GB | 1250 GB | $1.94/hr | $0.97/hr | ||
| L40Sx2 | 2× | 44 | 256 GB | 1250 GB | $1.94/hr | $0.97/hr | ||
| L40Sx2 | 2× | 44 | 256 GB | 1250 GB | $1.94/hr | $0.97/hr | ||
| L40Sx2 | 2× | 44 | 256 GB | 1250 GB | $1.94/hr | $0.97/hr | ||
| L40Sx2 | 2× | 44 | 256 GB | 1250 GB | $1.94/hr | $0.97/hr | ||
| 2L40S.32v.512m | 2× | 32 | 512 GB | — | $2.53/hr | $1.27/hr | ||
| 2L40S.32v.512m | 2× | 32 | 512 GB | — | $2.53/hr | $1.27/hr | ||
| 2L40S.32v.512m | 2× | 32 | 512 GB | — | $2.53/hr | $1.27/hr | ||
| L40Sx2 | 2× | 16 | 294 GB | 128 GB | $3.30/hr | $1.65/hr | ||
| 2x L40S_PCIE | 2× | 16 | 294 GB | 128 GB | $3.60/hr | $1.80/hr | ||
| N.L40S.192 | 2× | 24 | 192 GB | — | $4.13/hr | $2.06/hr | ||
| N.L40S.192 | 2× | 24 | 192 GB | — | $4.13/hr | $2.06/hr | ||
| N.L40S.192 | 2× | 24 | 192 GB | — | $4.13/hr | $2.06/hr | ||
| N.L40S.256 | 2× | 32 | 256 GB | — | $4.54/hr | $2.27/hr | ||
| N.L40S.256 | 2× | 32 | 256 GB | — | $4.54/hr | $2.27/hr | ||
| N.L40S.256 | 2× | 32 | 256 GB | — | $4.54/hr | $2.27/hr | ||
| 2x L40S_PCIE | 2× | 64 | 384 GB | 512 GB | $6.34/hr | $3.17/hr | ||
| 2x L40S_PCIE | 2× | 64 | 384 GB | 512 GB | $6.34/hr | $3.17/hr | ||
| 2x L40S_PCIE | 2× | 64 | 384 GB | 512 GB | $6.34/hr | $3.17/hr | ||
| 4x L40S_PCIE | 4× | 46 | 288 GB | 2500 GB | $3.84/hr | $0.96/hr | ||
| 4x L40S_PCIE | 4× | 46 | 288 GB | 2500 GB | $3.84/hr | $0.96/hr | ||
| 4x L40S_PCIE | 4× | 46 | 288 GB | 2500 GB | $3.84/hr | $0.96/hr | ||
| 4x L40S_PCIE | 4× | 46 | 288 GB | 2500 GB | $3.84/hr | $0.96/hr | ||
| 4x L40S_PCIE | 4× | 46 | 288 GB | 2500 GB | $3.84/hr | $0.96/hr | ||
| 4x L40S_PCIE | 4× | 46 | 288 GB | 2500 GB | $3.84/hr | $0.96/hr | ||
| 4x L40S_PCIE | 4× | 46 | 288 GB | 2500 GB | $3.84/hr | $0.96/hr | ||
| 4x L40S_PCIE | 4× | 46 | 288 GB | 2500 GB | $3.84/hr | $0.96/hr | ||
| 4x L40S_PCIE | 4× | 46 | 288 GB | 2500 GB | $3.84/hr | $0.96/hr | ||
| 4x L40S_PCIE | 4× | 46 | 288 GB | 2500 GB | $3.84/hr | $0.96/hr | ||
| 4x L40S_PCIE | 4× | 46 | 288 GB | 2500 GB | $3.84/hr | $0.96/hr | ||
| 4x L40S_PCIE | 4× | 46 | 288 GB | 2500 GB | $3.84/hr | $0.96/hr | ||
| 4x L40S_PCIE | 4× | 46 | 288 GB | 2500 GB | $3.84/hr | $0.96/hr | ||
| 4x L40S_PCIE | 4× | 46 | 288 GB | 2500 GB | $3.84/hr | $0.96/hr | ||
| L40Sx4 | 4× | 88 | 288 GB | 2500 GB | $3.87/hr | $0.97/hr | ||
| L40Sx4 | 4× | 88 | 288 GB | 2500 GB | $3.87/hr | $0.97/hr | ||
| L40Sx4 | 4× | 88 | 288 GB | 2500 GB | $3.87/hr | $0.97/hr | ||
| L40Sx4 | 4× | 88 | 288 GB | 2500 GB | $3.87/hr | $0.97/hr | ||
| L40Sx4 | 4× | 88 | 288 GB | 2500 GB | $3.87/hr | $0.97/hr | ||
| L40Sx4 | 4× | 88 | 288 GB | 2500 GB | $3.87/hr | $0.97/hr | ||
| L40Sx4 | 4× | 88 | 288 GB | 2500 GB | $3.87/hr | $0.97/hr | ||
| L40Sx4 | 4× | 88 | 288 GB | 2500 GB | $3.87/hr | $0.97/hr | ||
| L40Sx4 | 4× | 88 | 288 GB | 2500 GB | $3.87/hr | $0.97/hr | ||
| L40Sx4 | 4× | 88 | 288 GB | 2500 GB | $3.87/hr | $0.97/hr | ||
| L40Sx4 | 4× | 88 | 288 GB | 2500 GB | $3.87/hr | $0.97/hr | ||
| L40Sx4 | 4× | 88 | 288 GB | 2500 GB | $3.87/hr | $0.97/hr | ||
| L40Sx4 | 4× | 88 | 288 GB | 2500 GB | $3.87/hr | $0.97/hr | ||
| L40Sx4 | 4× | 88 | 288 GB | 2500 GB | $3.87/hr | $0.97/hr | ||
| L40Sx4 | 4× | 88 | 288 GB | 2500 GB | $3.87/hr | $0.97/hr | ||
| 4L40S.64v.1024m | 4× | 64 | 768 GB | — | $5.01/hr | $1.25/hr | ||
| 4L40S.64v.1024m | 4× | 64 | 768 GB | — | $5.01/hr | $1.25/hr | ||
| 4L40S.64v.1024m | 4× | 64 | 768 GB | — | $5.02/hr | $1.25/hr | ||
| L40Sx4 | 4× | 32 | 588 GB | 128 GB | $6.60/hr | $1.65/hr | ||
| 4x L40S_PCIE | 4× | 32 | 588 GB | 128 GB | $7.20/hr | $1.80/hr | ||
| N.L40S.512 | 4× | 64 | 512 GB | — | $9.09/hr | $2.27/hr | ||
| N.L40S.512 | 4× | 64 | 512 GB | — | $9.09/hr | $2.27/hr | ||
| N.L40S.512 | 4× | 64 | 512 GB | — | $9.09/hr | $2.27/hr | ||
| g6e.12xlarge | 4× | — | — | — | $10.49/hr | $2.62/hr | ||
| g6e.12xlarge | 4× | — | — | — | $10.49/hr | $2.62/hr | ||
| g6e.12xlarge | 4× | — | — | — | $10.49/hr | $2.62/hr | ||
| 4x L40S_PCIE | 4× | 128 | 768 GB | 512 GB | $12.61/hr | $3.15/hr | ||
| 4x L40S_PCIE | 4× | 128 | 768 GB | 512 GB | $12.61/hr | $3.15/hr | ||
| 4x L40S_PCIE | 4× | 128 | 768 GB | 512 GB | $12.61/hr | $3.15/hr | ||
| 4x L40S_PCIE | 4× | 128 | 768 GB | 512 GB | $12.61/hr | $3.15/hr | ||
| BM.GPU.L40S.4 | 4× | — | — | — | $14.00/hr | $3.50/hr | ||
| BM.GPU.L40S.4 | 4× | — | — | — | $14.00/hr | $3.50/hr | ||
| BM.GPU.L40S.4 | 4× | — | — | — | $14.00/hr | $3.50/hr | ||
| g6e.24xlarge | 4× | — | — | — | $15.07/hr | $3.77/hr | ||
| g6e.24xlarge | 4× | — | — | — | $15.07/hr | $3.77/hr | ||
| g6e.24xlarge | 4× | — | — | — | $15.07/hr | $3.77/hr | ||
| 8x L40S_PCIE | 8× | 94 | 576 GB | 5000 GB | $7.68/hr | $0.96/hr | ||
| 8x L40S_PCIE | 8× | 94 | 576 GB | 5000 GB | $7.68/hr | $0.96/hr | ||
| 8x L40S_PCIE | 8× | 94 | 576 GB | 5000 GB | $7.68/hr | $0.96/hr | ||
| 8L40S.64v.2048m | 8× | 64 | 1536 GB | — | $9.92/hr | $1.24/hr | ||
| 8L40S.64v.2048m | 8× | 64 | 1536 GB | — | $9.92/hr | $1.24/hr | ||
| 8L40S.64v.2048m | 8× | 64 | 1536 GB | — | $9.93/hr | $1.24/hr | ||
| g6e.48xlarge | 8× | — | — | — | $30.13/hr | $3.77/hr | ||
| g6e.48xlarge | 8× | — | — | — | $30.13/hr | $3.77/hr | ||
| g6e.48xlarge | 8× | — | — | — | $30.13/hr | $3.77/hr |
Looking for the cheapest rate?
Hyperscaler bundles include managed networking + SLAs. Raw per-GPU rental on P2P marketplaces is typically 3–10× cheaper.
See raw rental rates on the Overview tab →
FAQ
Cloud instances — common questions.
How much does it cost to rent the Nvidia L40S right now?
The cheapest current listing is $0.53/hr on Lium, and the median across the 12 providers listing it is $0.96/hr. Running one around the clock for a month (730 hours) at the cheapest rate costs about $387.
What AI models can the Nvidia L40S run?
With 48 GB it runs 70B models at 4-bit (about 35–40 GB of weights plus KV cache) and 32B models at INT8. It can QLoRA fine-tune models up to about 70B with short sequences, and 32B comfortably.
Which models are recommended for the Nvidia L40S?
32 models in our catalog have a recommended configuration for this card, with the quantization that fits its 48 GB — see the AI models tab.
Why does the Nvidia L40S cost different amounts on different providers?
Marketplaces such as Vast.ai and Clore.ai list machines from independent hosts who set their own prices, so competition pushes rates down but reliability varies by host. Operator clouds such as Lambda and the hyperscalers charge more for consistent hardware, support and networking. Prices here are per GPU, so they compare directly.
How is the Nvidia L40S price calculated?
We collect listings from each provider's public API or price page — every 5–10 minutes for marketplaces, up to daily for operator clouds — and show the median hourly price per provider from the last 24 hours, so one unusually cheap listing doesn't set the headline. Details are on the methodology page.
AI models
INT4
INT4
FP16
FP16
INT4
INT4
FP16
INT4
INT4
FP8
FP8
FP8
FP8
FP8
FP8
FP8
FP8
FP8
FP8
INT4
INT4
INT4
INT4
INT4
Models that run on this GPU.
GPU-count + quantization recommendations covering fine-tuning, inference, and run-it-yourself scenarios on the Nvidia L40S.
Qwen 2.5 72B
by Alibaba (Qwen Team)
Required GPUs
1× Nvidia L40S
Total VRAM
48 GB
Parameters
73B
Context
128K tokens
Qwen2.5 72B Instruct
by Alibaba (Qwen Team)
Required GPUs
1× Nvidia L40S
Total VRAM
48 GB
Parameters
72B
Context
33K tokens
DeepSeek R1 Distill Qwen 14B
by DeepSeek
Required GPUs
1× Nvidia L40S
Total VRAM
48 GB
Parameters
15B
Context
128K tokens
FLUX.1 Schnell
by Black Forest Labs
Required GPUs
1× Nvidia L40S
Total VRAM
48 GB
Parameters
12B
Qwen2 72B Instruct
by Togethercomputer
Required GPUs
1× Nvidia L40S
Total VRAM
48 GB
Parameters
72B
Context
33K tokens
Qwen2.5 72B Instruct Turbo
by Alibaba (Qwen Team)
Required GPUs
1× Nvidia L40S
Total VRAM
48 GB
Parameters
72B
Context
131K tokens
Gemma 3 27B
by Google DeepMind
Required GPUs
1× Nvidia L40S
Total VRAM
48 GB
Parameters
27B (27B active)
Context
128K tokens
Qwen2-VL (72B) Instruct
by Alibaba (Qwen Team)
Required GPUs
1× Nvidia L40S
Total VRAM
48 GB
Parameters
72B
Context
33K tokens
Qwen: Qwen2.5 VL 72B Instruct
by Alibaba (Qwen Team)
Required GPUs
1× Nvidia L40S
Total VRAM
48 GB
Parameters
72B
Context
131K tokens
Qwen 2.5 Coder 32B
by Alibaba (Qwen Team)
Required GPUs
1× Nvidia L40S
Total VRAM
48 GB
Parameters
33B
Context
128K tokens
DeepSeek R1 Distill Qwen 32B
by DeepSeek
Required GPUs
1× Nvidia L40S
Total VRAM
48 GB
Parameters
33B
Context
128K tokens
Qwen 2.5 32B
by Alibaba (Qwen Team)
Required GPUs
1× Nvidia L40S
Total VRAM
48 GB
Parameters
33B
Context
128K tokens
Qwen 3 32B
by Alibaba (Qwen Team)
Required GPUs
1× Nvidia L40S
Total VRAM
48 GB
Parameters
33B
Context
128K tokens
LLaVA 34B
by LLaVA Project
Required GPUs
1× Nvidia L40S
Total VRAM
48 GB
Parameters
34B
Context
4K tokens
Code Llama 34B
by Meta AI
Required GPUs
1× Nvidia L40S
Total VRAM
48 GB
Parameters
34B
Context
16K tokens
DeepSeek Coder 33B
by DeepSeek
Required GPUs
1× Nvidia L40S
Total VRAM
48 GB
Parameters
33B
Context
16K tokens
Yi-34B
by 01.AI
Required GPUs
1× Nvidia L40S
Total VRAM
48 GB
Parameters
34B
Context
32K tokens
Qwen: Qwen3.6 35B A3B
by Alibaba (Qwen Team)
Required GPUs
1× Nvidia L40S
Total VRAM
48 GB
Parameters
35B
Context
262K tokens
Qwen: Qwen3.5-35B-A3B
by Alibaba (Qwen Team)
Required GPUs
1× Nvidia L40S
Total VRAM
48 GB
Parameters
35B
Context
262K tokens
?
FP8
TheDrummer: Skyfall 36B V2
by Thedrummer
Required GPUs
1× Nvidia L40S
Total VRAM
48 GB
Parameters
36B
Context
33K tokens
Llama 3.3 70B
by Meta AI
Required GPUs
1× Nvidia L40S
Total VRAM
48 GB
Parameters
70B
Context
128K tokens
DeepSeek R1 Distill Llama 70B
by DeepSeek
Required GPUs
1× Nvidia L40S
Total VRAM
48 GB
Parameters
70B
Context
128K tokens
Llama 3.1 70B
by Meta AI
Required GPUs
1× Nvidia L40S
Total VRAM
48 GB
Parameters
70B
Context
128K tokens
Code Llama 70B
by Meta AI
Required GPUs
1× Nvidia L40S
Total VRAM
48 GB
Parameters
70B
Context
16K tokens
?
INT4
Hermes 3 70B
by Nous Research
Required GPUs
1× Nvidia L40S
Total VRAM
48 GB
Parameters
70B
Context
128K tokens
?
INT4
Nous: Hermes 4 70B
by Nous Research
Required GPUs
1× Nvidia L40S
Total VRAM
48 GB
Parameters
70B
Context
131K tokens
?
INT4
Sao10K: Llama 3.1 70B Hanami x1
by Sao10k
Required GPUs
1× Nvidia L40S
Total VRAM
48 GB
Parameters
70B
Context
16K tokens
?
INT4
Sao10K: Llama 3.3 Euryale 70B
by Sao10k
Required GPUs
1× Nvidia L40S
Total VRAM
48 GB
Parameters
70B
Context
131K tokens
?
INT4
Magnum v4 72B
by Anthracite Org
Required GPUs
1× Nvidia L40S
Total VRAM
48 GB
Parameters
72B
Context
33K tokens
?
INT4
Sao10K: Llama 3.1 Euryale 70B v2.2
by Sao10k
Required GPUs
1× Nvidia L40S
Total VRAM
48 GB
Parameters
70B
Context
131K tokens
?
INT4
Sao10k: Llama 3 Euryale 70B v2.1
by Sao10k
Required GPUs
1× Nvidia L40S
Total VRAM
48 GB
Parameters
70B
Context
8K tokens
Meta: Llama 3 70B Instruct
by Meta AI
Required GPUs
1× Nvidia L40S
Total VRAM
48 GB
Parameters
70B
Context
8K tokens
Renting for inference?
Pair these models with the cheapest provider on the rental table.
See rental rates on the Overview tab →
FAQ
AI models on this GPU.
How much does it cost to rent the Nvidia L40S right now?
The cheapest current listing is $0.53/hr on Lium, and the median across the 12 providers listing it is $0.96/hr. Running one around the clock for a month (730 hours) at the cheapest rate costs about $387.
What AI models can the Nvidia L40S run?
With 48 GB it runs 70B models at 4-bit (about 35–40 GB of weights plus KV cache) and 32B models at INT8. It can QLoRA fine-tune models up to about 70B with short sequences, and 32B comfortably.
Which models are recommended for the Nvidia L40S?
32 models in our catalog have a recommended configuration for this card, with the quantization that fits its 48 GB — see the AI models tab.
Why does the Nvidia L40S cost different amounts on different providers?
Marketplaces such as Vast.ai and Clore.ai list machines from independent hosts who set their own prices, so competition pushes rates down but reliability varies by host. Operator clouds such as Lambda and the hyperscalers charge more for consistent hardware, support and networking. Prices here are per GPU, so they compare directly.
How is the Nvidia L40S price calculated?
We collect listings from each provider's public API or price page — every 5–10 minutes for marketplaces, up to daily for operator clouds — and show the median hourly price per provider from the last 24 hours, so one unusually cheap listing doesn't set the headline. Details are on the methodology page.