datacenter
Louer Nvidia L40.
Ada Lovelace
48GB VRAM
From $0.69/hr
Per hour
$0.69
Per day
$16.56
Per week
$115.92
Per month
$497
Provider spread
6 providers ·
up to 31% cheaper at the low end
Cheapest · $0.69/hr on RunPod
Median $0.94/hr
Most expensive · $1.00/hr on Hyperstack
Price history
Daily median across providers.
Loading...
Where to rent it
All providers carrying this GPU.
AI models that fit
See all 6 →
Run these on this GPU.
- Qwen 2.5 72B 1× · int4
- Qwen2.5 72B Instruct 1× · int4
- Qwen2 72B Instruct 1× · int4
Cloud instances
See all 161 →
Hyperscaler bundles.
Pre-configured on 4 clouds — from $0.79/hr total
($0.79/hr per GPU).
FAQ
Frequently asked.
How much does it cost to rent the Nvidia L40 right now?
The cheapest current listing is $0.69/hr on RunPod, and the median across the 6 providers listing it is $0.94/hr. Running one around the clock for a month (730 hours) at the cheapest rate costs about $504.
What AI models can the Nvidia L40 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 L40?
6 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 L40 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 L40 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
$0.79/hr
Lowest $/hr per GPU
$0.79/hr
Providers
4
Instance shapes
161
| Provider | Instance | GPUs | vCPU | RAM | Disk | $/hr | $/hr per GPU | |
|---|---|---|---|---|---|---|---|---|
| l40_x1 | 1× | 6 | 48 GB | 100 GB | $0.79/hr | $0.79/hr | ||
| l40_x1 | 1× | 6 | 48 GB | 100 GB | $0.79/hr | $0.79/hr | ||
| l40_x1 | 1× | 6 | 48 GB | 100 GB | $0.79/hr | $0.79/hr | ||
| 1x L40_PCIE | 1× | 14 | 72 GB | 625 GB | $0.94/hr | $0.94/hr | ||
| 1x L40_PCIE | 1× | 14 | 72 GB | 625 GB | $0.94/hr | $0.94/hr | ||
| 1x L40_PCIE | 1× | 14 | 72 GB | 625 GB | $0.94/hr | $0.94/hr | ||
| 1x L40_PCIE | 1× | 14 | 72 GB | 625 GB | $0.94/hr | $0.94/hr | ||
| 1x L40_PCIE | 1× | 14 | 72 GB | 625 GB | $0.94/hr | $0.94/hr | ||
| 1x L40_PCIE | 1× | 14 | 72 GB | 625 GB | $0.94/hr | $0.94/hr | ||
| 1x L40_PCIE | 1× | 14 | 72 GB | 625 GB | $0.94/hr | $0.94/hr | ||
| 1x L40_PCIE | 1× | 14 | 72 GB | 625 GB | $0.94/hr | $0.94/hr | ||
| 1x L40_PCIE | 1× | 14 | 72 GB | 625 GB | $0.94/hr | $0.94/hr | ||
| 1x L40_PCIE | 1× | 14 | 72 GB | 625 GB | $0.94/hr | $0.94/hr | ||
| 1x L40_PCIE | 1× | 14 | 72 GB | 625 GB | $0.94/hr | $0.94/hr | ||
| 1x L40_PCIE | 1× | 14 | 72 GB | 625 GB | $0.94/hr | $0.94/hr | ||
| 1x L40_PCIE | 1× | 14 | 72 GB | 625 GB | $0.94/hr | $0.94/hr | ||
| 1x L40_PCIE | 1× | 14 | 72 GB | 625 GB | $0.94/hr | $0.94/hr | ||
| 1x L40_PCIE | 1× | 14 | 72 GB | 625 GB | $0.94/hr | $0.94/hr | ||
| 1x L40_PCIE | 1× | 14 | 72 GB | 625 GB | $0.94/hr | $0.94/hr | ||
| 1x L40_PCIE | 1× | 14 | 72 GB | 625 GB | $0.94/hr | $0.94/hr | ||
| L40 | 1× | 26 | 192 GB | 625 GB | $0.97/hr | $0.97/hr | ||
| L40 | 1× | 26 | 192 GB | 625 GB | $0.97/hr | $0.97/hr | ||
| L40 | 1× | 26 | 192 GB | 625 GB | $0.97/hr | $0.97/hr | ||
| L40 | 1× | 26 | 192 GB | 625 GB | $0.97/hr | $0.97/hr | ||
| L40 | 1× | 26 | 192 GB | 625 GB | $0.97/hr | $0.97/hr | ||
| L40 | 1× | 26 | 192 GB | 625 GB | $0.97/hr | $0.97/hr | ||
| L40 | 1× | 26 | 192 GB | 625 GB | $0.97/hr | $0.97/hr | ||
| L40 | 1× | 26 | 192 GB | 625 GB | $0.97/hr | $0.97/hr | ||
| L40 | 1× | 26 | 192 GB | 625 GB | $0.97/hr | $0.97/hr | ||
| L40 | 1× | 26 | 192 GB | 625 GB | $0.97/hr | $0.97/hr | ||
| L40 | 1× | 26 | 192 GB | 625 GB | $0.97/hr | $0.97/hr | ||
| L40 | 1× | 26 | 192 GB | 625 GB | $0.97/hr | $0.97/hr | ||
| L40 | 1× | 26 | 192 GB | 625 GB | $0.97/hr | $0.97/hr | ||
| L40 | 1× | 26 | 192 GB | 625 GB | $0.97/hr | $0.97/hr | ||
| L40 | 1× | 26 | 192 GB | 625 GB | $0.97/hr | $0.97/hr | ||
| L40 | 1× | 26 | 192 GB | 625 GB | $0.97/hr | $0.97/hr | ||
| L40 | 1× | 26 | 192 GB | 625 GB | $0.97/hr | $0.97/hr | ||
| L40 | 1× | 26 | 192 GB | 625 GB | $0.97/hr | $0.97/hr | ||
| on-demand · L40 | 1× | 28 | 120 GB | — | $1.00/hr | $1.00/hr | ||
| on-demand · L40 | 1× | 28 | 120 GB | — | $1.00/hr | $1.00/hr | ||
| on-demand · L40 | 1× | 28 | 120 GB | — | $1.00/hr | $1.00/hr | ||
| l40_x2 | 2× | 12 | 96 GB | 100 GB | $1.58/hr | $0.79/hr | ||
| l40_x2 | 2× | 12 | 96 GB | 100 GB | $1.58/hr | $0.79/hr | ||
| l40_x2 | 2× | 12 | 96 GB | 100 GB | $1.58/hr | $0.79/hr | ||
| 2x L40_PCIE | 2× | 26 | 144 GB | 1250 GB | $1.87/hr | $0.94/hr | ||
| 2x L40_PCIE | 2× | 26 | 144 GB | 1250 GB | $1.87/hr | $0.94/hr | ||
| 2x L40_PCIE | 2× | 26 | 144 GB | 1250 GB | $1.87/hr | $0.94/hr | ||
| 2x L40_PCIE | 2× | 26 | 144 GB | 1250 GB | $1.87/hr | $0.94/hr | ||
| 2x L40_PCIE | 2× | 26 | 144 GB | 1250 GB | $1.87/hr | $0.94/hr | ||
| 2x L40_PCIE | 2× | 26 | 144 GB | 1250 GB | $1.87/hr | $0.94/hr | ||
| 2x L40_PCIE | 2× | 26 | 144 GB | 1250 GB | $1.87/hr | $0.94/hr | ||
| 2x L40_PCIE | 2× | 26 | 144 GB | 1250 GB | $1.87/hr | $0.94/hr | ||
| 2x L40_PCIE | 2× | 26 | 144 GB | 1250 GB | $1.87/hr | $0.94/hr | ||
| 2x L40_PCIE | 2× | 26 | 144 GB | 1250 GB | $1.87/hr | $0.94/hr | ||
| 2x L40_PCIE | 2× | 26 | 144 GB | 1250 GB | $1.87/hr | $0.94/hr | ||
| 2x L40_PCIE | 2× | 26 | 144 GB | 1250 GB | $1.87/hr | $0.94/hr | ||
| 2x L40_PCIE | 2× | 26 | 144 GB | 1250 GB | $1.87/hr | $0.94/hr | ||
| 2x L40_PCIE | 2× | 26 | 144 GB | 1250 GB | $1.87/hr | $0.94/hr | ||
| 2x L40_PCIE | 2× | 26 | 144 GB | 1250 GB | $1.87/hr | $0.94/hr | ||
| 2x L40_PCIE | 2× | 26 | 144 GB | 1250 GB | $1.87/hr | $0.94/hr | ||
| 2x L40_PCIE | 2× | 26 | 144 GB | 1250 GB | $1.87/hr | $0.94/hr | ||
| L40x2 | 2× | 50 | 384 GB | 1250 GB | $2.18/hr | $1.09/hr | ||
| L40x2 | 2× | 50 | 384 GB | 1250 GB | $2.18/hr | $1.09/hr | ||
| L40x2 | 2× | 50 | 384 GB | 1250 GB | $2.18/hr | $1.09/hr | ||
| L40x2 | 2× | 50 | 384 GB | 1250 GB | $2.18/hr | $1.09/hr | ||
| L40x2 | 2× | 50 | 384 GB | 1250 GB | $2.18/hr | $1.09/hr | ||
| L40x2 | 2× | 50 | 384 GB | 1250 GB | $2.18/hr | $1.09/hr | ||
| L40x2 | 2× | 50 | 384 GB | 1250 GB | $2.18/hr | $1.09/hr | ||
| L40x2 | 2× | 50 | 384 GB | 1250 GB | $2.18/hr | $1.09/hr | ||
| L40x2 | 2× | 50 | 384 GB | 1250 GB | $2.18/hr | $1.09/hr | ||
| L40x2 | 2× | 50 | 384 GB | 1250 GB | $2.18/hr | $1.09/hr | ||
| L40x2 | 2× | 50 | 384 GB | 1250 GB | $2.18/hr | $1.09/hr | ||
| L40x2 | 2× | 50 | 384 GB | 1250 GB | $2.18/hr | $1.09/hr | ||
| L40x2 | 2× | 50 | 384 GB | 1250 GB | $2.18/hr | $1.09/hr | ||
| L40x2 | 2× | 50 | 384 GB | 1250 GB | $2.18/hr | $1.09/hr | ||
| L40x2 | 2× | 50 | 384 GB | 1250 GB | $2.18/hr | $1.09/hr | ||
| L40x2 | 2× | 50 | 384 GB | 1250 GB | $2.18/hr | $1.09/hr | ||
| L40x2 | 2× | 50 | 384 GB | 1250 GB | $2.18/hr | $1.09/hr | ||
| L40x2 | 2× | 50 | 384 GB | 1250 GB | $2.18/hr | $1.09/hr | ||
| 4x L40_PCIE | 4× | 50 | 288 GB | 2500 GB | $3.74/hr | $0.94/hr | ||
| 4x L40_PCIE | 4× | 50 | 288 GB | 2500 GB | $3.74/hr | $0.94/hr | ||
| 4x L40_PCIE | 4× | 50 | 288 GB | 2500 GB | $3.74/hr | $0.94/hr | ||
| 4x L40_PCIE | 4× | 50 | 288 GB | 2500 GB | $3.74/hr | $0.94/hr | ||
| 4x L40_PCIE | 4× | 50 | 288 GB | 2500 GB | $3.74/hr | $0.94/hr | ||
| 4x L40_PCIE | 4× | 50 | 288 GB | 2500 GB | $3.74/hr | $0.94/hr | ||
| 4x L40_PCIE | 4× | 50 | 288 GB | 2500 GB | $3.74/hr | $0.94/hr | ||
| 4x L40_PCIE | 4× | 50 | 288 GB | 2500 GB | $3.74/hr | $0.94/hr | ||
| 4x L40_PCIE | 4× | 50 | 288 GB | 2500 GB | $3.74/hr | $0.94/hr | ||
| 4x L40_PCIE | 4× | 50 | 288 GB | 2500 GB | $3.74/hr | $0.94/hr | ||
| 4x L40_PCIE | 4× | 50 | 288 GB | 2500 GB | $3.74/hr | $0.94/hr | ||
| 4x L40_PCIE | 4× | 50 | 288 GB | 2500 GB | $3.74/hr | $0.94/hr | ||
| 4x L40_PCIE | 4× | 50 | 288 GB | 2500 GB | $3.74/hr | $0.94/hr | ||
| 4x L40_PCIE | 4× | 50 | 288 GB | 2500 GB | $3.74/hr | $0.94/hr | ||
| 4x L40_PCIE | 4× | 50 | 288 GB | 2500 GB | $3.74/hr | $0.94/hr | ||
| 4x L40_PCIE | 4× | 50 | 288 GB | 2500 GB | $3.74/hr | $0.94/hr | ||
| 4x L40_PCIE | 4× | 50 | 288 GB | 2500 GB | $3.74/hr | $0.94/hr | ||
| l40_x4 | 4× | 24 | 192 GB | 100 GB | $3.96/hr | $0.99/hr | ||
| l40_x4 | 4× | 24 | 192 GB | 100 GB | $3.96/hr | $0.99/hr | ||
| l40_x4 | 4× | 24 | 192 GB | 100 GB | $3.96/hr | $0.99/hr | ||
| L40x4 | 4× | 126 | 232 GB | 3300 GB | $4.40/hr | $1.10/hr | ||
| L40x4 | 4× | 126 | 232 GB | 3300 GB | $4.40/hr | $1.10/hr | ||
| L40x4 | 4× | 126 | 232 GB | 3300 GB | $4.40/hr | $1.10/hr | ||
| L40x4 | 4× | 126 | 232 GB | 3300 GB | $4.40/hr | $1.10/hr | ||
| L40x4 | 4× | 126 | 232 GB | 3300 GB | $4.40/hr | $1.10/hr | ||
| L40x4 | 4× | 126 | 232 GB | 3300 GB | $4.40/hr | $1.10/hr | ||
| L40x4 | 4× | 126 | 232 GB | 3300 GB | $4.40/hr | $1.10/hr | ||
| L40x4 | 4× | 126 | 232 GB | 3300 GB | $4.40/hr | $1.10/hr | ||
| L40x4 | 4× | 126 | 232 GB | 3300 GB | $4.40/hr | $1.10/hr | ||
| L40x4 | 4× | 126 | 232 GB | 3300 GB | $4.40/hr | $1.10/hr | ||
| L40x4 | 4× | 126 | 232 GB | 3300 GB | $4.40/hr | $1.10/hr | ||
| L40x4 | 4× | 126 | 232 GB | 3300 GB | $4.40/hr | $1.10/hr | ||
| L40x4 | 4× | 126 | 232 GB | 3300 GB | $4.40/hr | $1.10/hr | ||
| L40x4 | 4× | 126 | 232 GB | 3300 GB | $4.40/hr | $1.10/hr | ||
| L40x4 | 4× | 126 | 232 GB | 3300 GB | $4.40/hr | $1.10/hr | ||
| L40x4 | 4× | 126 | 232 GB | 3300 GB | $4.40/hr | $1.10/hr | ||
| L40x4 | 4× | 126 | 232 GB | 3300 GB | $4.40/hr | $1.10/hr | ||
| L40x4 | 4× | 126 | 232 GB | 3300 GB | $4.40/hr | $1.10/hr | ||
| l40_x8 | 8× | 48 | 384 GB | 100 GB | $7.92/hr | $0.99/hr | ||
| l40_x8 | 8× | 48 | 384 GB | 100 GB | $7.92/hr | $0.99/hr | ||
| l40_x8 | 8× | 48 | 384 GB | 100 GB | $7.92/hr | $0.99/hr | ||
| 8x L40_PCIE | 8× | 252 | 464 GB | 6600 GB | $8.46/hr | $1.06/hr | ||
| 8x L40_PCIE | 8× | 252 | 464 GB | 6600 GB | $8.46/hr | $1.06/hr | ||
| 8x L40_PCIE | 8× | 252 | 464 GB | 6600 GB | $8.46/hr | $1.06/hr | ||
| 8x L40_PCIE | 8× | 252 | 464 GB | 6600 GB | $8.46/hr | $1.06/hr | ||
| 8x L40_PCIE | 8× | 252 | 464 GB | 6600 GB | $8.46/hr | $1.06/hr | ||
| 8x L40_PCIE | 8× | 252 | 464 GB | 6600 GB | $8.46/hr | $1.06/hr | ||
| 8x L40_PCIE | 8× | 252 | 464 GB | 6600 GB | $8.46/hr | $1.06/hr | ||
| 8x L40_PCIE | 8× | 252 | 464 GB | 6600 GB | $8.46/hr | $1.06/hr | ||
| 8x L40_PCIE | 8× | 252 | 464 GB | 6600 GB | $8.46/hr | $1.06/hr | ||
| 8x L40_PCIE | 8× | 252 | 464 GB | 6600 GB | $8.46/hr | $1.06/hr | ||
| 8x L40_PCIE | 8× | 252 | 464 GB | 6600 GB | $8.46/hr | $1.06/hr | ||
| L40x8 | 8× | 252 | 464 GB | 6600 GB | $8.80/hr | $1.10/hr | ||
| L40x8 | 8× | 252 | 464 GB | 6600 GB | $8.80/hr | $1.10/hr | ||
| L40x8 | 8× | 252 | 464 GB | 6600 GB | $8.80/hr | $1.10/hr | ||
| L40x8 | 8× | 252 | 464 GB | 6600 GB | $8.80/hr | $1.10/hr | ||
| L40x8 | 8× | 252 | 464 GB | 6600 GB | $8.80/hr | $1.10/hr | ||
| L40x8 | 8× | 252 | 464 GB | 6600 GB | $8.80/hr | $1.10/hr | ||
| L40x8 | 8× | 252 | 464 GB | 6600 GB | $8.80/hr | $1.10/hr | ||
| L40x8 | 8× | 252 | 464 GB | 6600 GB | $8.80/hr | $1.10/hr | ||
| L40x8 | 8× | 252 | 464 GB | 6600 GB | $8.80/hr | $1.10/hr | ||
| L40x8 | 8× | 252 | 464 GB | 6600 GB | $8.80/hr | $1.10/hr | ||
| L40x8 | 8× | 252 | 464 GB | 6600 GB | $8.80/hr | $1.10/hr | ||
| L40x8 | 8× | 252 | 464 GB | 6600 GB | $8.80/hr | $1.10/hr | ||
| L40x8_2 | 8× | 240 | 1892 GB | 7154 GB | $12.10/hr | $1.51/hr | ||
| L40x8_2 | 8× | 240 | 1892 GB | 7154 GB | $12.10/hr | $1.51/hr | ||
| L40x8_2 | 8× | 240 | 1892 GB | 7154 GB | $12.10/hr | $1.51/hr | ||
| L40x8_2 | 8× | 240 | 1892 GB | 7154 GB | $12.10/hr | $1.51/hr | ||
| L40x8_2 | 8× | 240 | 1892 GB | 7154 GB | $12.10/hr | $1.51/hr | ||
| L40x8_2 | 8× | 240 | 1892 GB | 7154 GB | $12.10/hr | $1.51/hr | ||
| L40x8_2 | 8× | 240 | 1892 GB | 7154 GB | $12.10/hr | $1.51/hr | ||
| L40x8_2 | 8× | 240 | 1892 GB | 7154 GB | $12.10/hr | $1.51/hr | ||
| L40x8_2 | 8× | 240 | 1892 GB | 7154 GB | $12.10/hr | $1.51/hr | ||
| L40x8_2 | 8× | 240 | 1892 GB | 7154 GB | $12.10/hr | $1.51/hr | ||
| L40x8_2 | 8× | 240 | 1892 GB | 7154 GB | $12.10/hr | $1.51/hr | ||
| L40x8_2 | 8× | 240 | 1892 GB | 7154 GB | $12.10/hr | $1.51/hr | ||
| L40x8_2 | 8× | 240 | 1892 GB | 7154 GB | $12.10/hr | $1.51/hr | ||
| L40x8_2 | 8× | 240 | 1892 GB | 7154 GB | $12.10/hr | $1.51/hr | ||
| L40x8_2 | 8× | 240 | 1892 GB | 7154 GB | $12.10/hr | $1.51/hr | ||
| L40x8_2 | 8× | 240 | 1892 GB | 7154 GB | $12.10/hr | $1.51/hr | ||
| L40x8_2 | 8× | 240 | 1892 GB | 7154 GB | $12.10/hr | $1.51/hr | ||
| L40x8_2 | 8× | 240 | 1892 GB | 7154 GB | $12.10/hr | $1.51/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 L40 right now?
The cheapest current listing is $0.69/hr on RunPod, and the median across the 6 providers listing it is $0.94/hr. Running one around the clock for a month (730 hours) at the cheapest rate costs about $504.
What AI models can the Nvidia L40 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 L40?
6 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 L40 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 L40 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
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 L40.
Qwen 2.5 72B
by Alibaba (Qwen Team)
Required GPUs
1× Nvidia L40
Total VRAM
48 GB
Parameters
73B
Context
128K tokens
Qwen2.5 72B Instruct
by Alibaba (Qwen Team)
Required GPUs
1× Nvidia L40
Total VRAM
48 GB
Parameters
72B
Context
33K tokens
Qwen2 72B Instruct
by Togethercomputer
Required GPUs
1× Nvidia L40
Total VRAM
48 GB
Parameters
72B
Context
33K tokens
Qwen2.5 72B Instruct Turbo
by Alibaba (Qwen Team)
Required GPUs
1× Nvidia L40
Total VRAM
48 GB
Parameters
72B
Context
131K tokens
Qwen2-VL (72B) Instruct
by Alibaba (Qwen Team)
Required GPUs
1× Nvidia L40
Total VRAM
48 GB
Parameters
72B
Context
33K tokens
Qwen: Qwen2.5 VL 72B Instruct
by Alibaba (Qwen Team)
Required GPUs
1× Nvidia L40
Total VRAM
48 GB
Parameters
72B
Context
131K 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 L40 right now?
The cheapest current listing is $0.69/hr on RunPod, and the median across the 6 providers listing it is $0.94/hr. Running one around the clock for a month (730 hours) at the cheapest rate costs about $504.
What AI models can the Nvidia L40 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 L40?
6 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 L40 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 L40 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.