datacenter
Louer Nvidia L4.
Ada Lovelace
24GB VRAM
From $0.083/hr
Per hour
$0.083
Per day
$2.00
Per week
$13.99
Per month
$60
Provider spread
7 providers ·
up to 93% cheaper at the low end
Cheapest · $0.083/hr on Clore.ai
Median $0.80/hr
Most expensive · $1.14/hr on Spheron Network
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 13 →
Run these on this GPU.
- TheDrummer: Skyfall 36B V2 1× · int4
- Whisper Large v3 1× · fp16
- Whisper Medium 1× · fp16
Cloud instances
See all 92 →
Hyperscaler bundles.
Pre-configured on 4 clouds — from $0.32/hr total
($0.32/hr per GPU).
FAQ
Frequently asked.
How much does it cost to rent the Nvidia L4 right now?
The cheapest current listing is $0.083/hr on Clore.ai, and the median across the 7 providers listing it is $0.80/hr. Running one around the clock for a month (730 hours) at the cheapest rate costs about $61.
What AI models can the Nvidia L4 run?
With 24 GB it runs 7–8B models at FP16, 13–14B at INT8 and about 32B at 4-bit. A 70B model needs a 48 GB card or two 24 GB cards. It can QLoRA fine-tune 7–14B models.
Which models are recommended for the Nvidia L4?
13 models in our catalog have a recommended configuration for this card, with the quantization that fits its 24 GB — see the AI models tab.
Why does the Nvidia L4 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 L4 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
$0.32/hr
Lowest $/hr per GPU
$0.32/hr
Providers
4
Instance shapes
92
| Provider | Instance | GPUs | vCPU | RAM | Disk | $/hr | $/hr per GPU | |
|---|---|---|---|---|---|---|---|---|
| community-1x | 1× | — | — | — | $0.32/hr | $0.32/hr | ||
| community-1x | 1× | — | — | — | $0.32/hr | $0.32/hr | ||
| community-1x | 1× | — | — | — | $0.32/hr | $0.32/hr | ||
| community-1x | 1× | — | — | — | $0.32/hr | $0.32/hr | ||
| community-1x | 1× | — | — | — | $0.32/hr | $0.32/hr | ||
| community-1x | 1× | — | — | — | $0.32/hr | $0.32/hr | ||
| community-1x | 1× | — | — | — | $0.32/hr | $0.32/hr | ||
| community-1x | 1× | — | — | — | $0.32/hr | $0.32/hr | ||
| community-1x | 1× | — | — | — | $0.32/hr | $0.32/hr | ||
| community-1x | 1× | — | — | — | $0.32/hr | $0.32/hr | ||
| community-1x | 1× | — | — | — | $0.32/hr | $0.32/hr | ||
| community-1x | 1× | — | — | — | $0.32/hr | $0.32/hr | ||
| community-1x | 1× | — | — | — | $0.32/hr | $0.32/hr | ||
| community-1x | 1× | — | — | — | $0.32/hr | $0.32/hr | ||
| community-1x | 1× | — | — | — | $0.32/hr | $0.32/hr | ||
| community-1x | 1× | — | — | — | $0.32/hr | $0.32/hr | ||
| community-1x | 1× | — | — | — | $0.32/hr | $0.32/hr | ||
| community-1x | 1× | — | — | — | $0.32/hr | $0.32/hr | ||
| g6.xlarge | 1× | — | — | — | $0.80/hr | $0.80/hr | ||
| g6.xlarge | 1× | — | — | — | $0.80/hr | $0.80/hr | ||
| g6.xlarge | 1× | — | — | — | $0.80/hr | $0.80/hr | ||
| g6.2xlarge | 1× | — | — | — | $0.98/hr | $0.98/hr | ||
| g6.2xlarge | 1× | — | — | — | $0.98/hr | $0.98/hr | ||
| g6.2xlarge | 1× | — | — | — | $0.98/hr | $0.98/hr | ||
| L4 | 1× | 8 | 48 GB | 500 GB | $1.04/hr | $1.04/hr | ||
| L4 | 1× | 8 | 48 GB | 500 GB | $1.04/hr | $1.04/hr | ||
| L4 | 1× | 8 | 48 GB | 500 GB | $1.04/hr | $1.04/hr | ||
| L4 | 1× | 8 | 48 GB | 500 GB | $1.04/hr | $1.04/hr | ||
| L4 | 1× | 8 | 48 GB | 500 GB | $1.04/hr | $1.04/hr | ||
| L4 | 1× | 8 | 48 GB | 500 GB | $1.04/hr | $1.04/hr | ||
| L4 | 1× | 8 | 48 GB | 500 GB | $1.04/hr | $1.04/hr | ||
| L4 | 1× | 8 | 48 GB | 500 GB | $1.04/hr | $1.04/hr | ||
| L4 | 1× | 8 | 48 GB | 500 GB | $1.04/hr | $1.04/hr | ||
| L4 | 1× | 8 | 48 GB | 500 GB | $1.04/hr | $1.04/hr | ||
| L4 | 1× | 8 | 48 GB | 500 GB | $1.04/hr | $1.04/hr | ||
| L4 | 1× | 8 | 48 GB | 500 GB | $1.04/hr | $1.04/hr | ||
| L4 | 1× | 8 | 48 GB | 500 GB | $1.04/hr | $1.04/hr | ||
| L4 | 1× | 8 | 48 GB | 500 GB | $1.04/hr | $1.04/hr | ||
| 1x L4_PCIE | 1× | 8 | 48 GB | 500 GB | $1.14/hr | $1.14/hr | ||
| 1x L4_PCIE | 1× | 8 | 48 GB | 500 GB | $1.14/hr | $1.14/hr | ||
| 1x L4_PCIE | 1× | 8 | 48 GB | 500 GB | $1.14/hr | $1.14/hr | ||
| 1x L4_PCIE | 1× | 8 | 48 GB | 500 GB | $1.14/hr | $1.14/hr | ||
| 1x L4_PCIE | 1× | 8 | 48 GB | 500 GB | $1.14/hr | $1.14/hr | ||
| 1x L4_PCIE | 1× | 8 | 48 GB | 500 GB | $1.14/hr | $1.14/hr | ||
| 1x L4_PCIE | 1× | 8 | 48 GB | 500 GB | $1.14/hr | $1.14/hr | ||
| 1x L4_PCIE | 1× | 8 | 48 GB | 500 GB | $1.14/hr | $1.14/hr | ||
| 1x L4_PCIE | 1× | 8 | 48 GB | 500 GB | $1.14/hr | $1.14/hr | ||
| 1x L4_PCIE | 1× | 8 | 48 GB | 500 GB | $1.14/hr | $1.14/hr | ||
| 1x L4_PCIE | 1× | 8 | 48 GB | 500 GB | $1.14/hr | $1.14/hr | ||
| 1x L4_PCIE | 1× | 8 | 48 GB | 500 GB | $1.14/hr | $1.14/hr | ||
| 1x L4_PCIE | 1× | 8 | 48 GB | 500 GB | $1.14/hr | $1.14/hr | ||
| 1x L4_PCIE | 1× | 8 | 48 GB | 500 GB | $1.14/hr | $1.14/hr | ||
| g6.4xlarge | 1× | — | — | — | $1.32/hr | $1.32/hr | ||
| g6.4xlarge | 1× | — | — | — | $1.32/hr | $1.32/hr | ||
| g6.4xlarge | 1× | — | — | — | $1.32/hr | $1.32/hr | ||
| gr6.4xlarge | 1× | — | — | — | $1.54/hr | $1.54/hr | ||
| gr6.4xlarge | 1× | — | — | — | $1.54/hr | $1.54/hr | ||
| gr6.4xlarge | 1× | — | — | — | $1.54/hr | $1.54/hr | ||
| g6.8xlarge | 1× | — | — | — | $2.01/hr | $2.01/hr | ||
| g6.8xlarge | 1× | — | — | — | $2.01/hr | $2.01/hr | ||
| g6.8xlarge | 1× | — | — | — | $2.01/hr | $2.01/hr | ||
| gr6.8xlarge | 1× | — | — | — | $2.45/hr | $2.45/hr | ||
| gr6.8xlarge | 1× | — | — | — | $2.45/hr | $2.45/hr | ||
| gr6.8xlarge | 1× | — | — | — | $2.45/hr | $2.45/hr | ||
| g6.16xlarge | 1× | — | — | — | $3.40/hr | $3.40/hr | ||
| g6.16xlarge | 1× | — | — | — | $3.40/hr | $3.40/hr | ||
| g6.16xlarge | 1× | — | — | — | $3.40/hr | $3.40/hr | ||
| L4x2 | 2× | 16 | 96 GB | 500 GB | $2.09/hr | $1.04/hr | ||
| L4x2 | 2× | 16 | 96 GB | 500 GB | $2.09/hr | $1.04/hr | ||
| L4x2 | 2× | 16 | 96 GB | 500 GB | $2.09/hr | $1.04/hr | ||
| L4x2 | 2× | 16 | 96 GB | 500 GB | $2.09/hr | $1.04/hr | ||
| L4x2 | 2× | 16 | 96 GB | 500 GB | $2.09/hr | $1.04/hr | ||
| L4x2 | 2× | 16 | 96 GB | 500 GB | $2.09/hr | $1.04/hr | ||
| L4x2 | 2× | 16 | 96 GB | 500 GB | $2.09/hr | $1.04/hr | ||
| L4x2 | 2× | 16 | 96 GB | 500 GB | $2.09/hr | $1.04/hr | ||
| L4x2 | 2× | 16 | 96 GB | 500 GB | $2.09/hr | $1.04/hr | ||
| 2x L4_PCIE | 2× | 16 | 96 GB | 500 GB | $2.28/hr | $1.14/hr | ||
| 2x L4_PCIE | 2× | 16 | 96 GB | 500 GB | $2.28/hr | $1.14/hr | ||
| 2x L4_PCIE | 2× | 16 | 96 GB | 500 GB | $2.28/hr | $1.14/hr | ||
| 2x L4_PCIE | 2× | 16 | 96 GB | 500 GB | $2.28/hr | $1.14/hr | ||
| 2x L4_PCIE | 2× | 16 | 96 GB | 500 GB | $2.28/hr | $1.14/hr | ||
| 2x L4_PCIE | 2× | 16 | 96 GB | 500 GB | $2.28/hr | $1.14/hr | ||
| 2x L4_PCIE | 2× | 16 | 96 GB | 500 GB | $2.28/hr | $1.14/hr | ||
| g6.12xlarge | 4× | — | — | — | $4.60/hr | $1.15/hr | ||
| g6.12xlarge | 4× | — | — | — | $4.60/hr | $1.15/hr | ||
| g6.12xlarge | 4× | — | — | — | $4.60/hr | $1.15/hr | ||
| g6.24xlarge | 4× | — | — | — | $6.68/hr | $1.67/hr | ||
| g6.24xlarge | 4× | — | — | — | $6.68/hr | $1.67/hr | ||
| g6.24xlarge | 4× | — | — | — | $6.68/hr | $1.67/hr | ||
| g6.48xlarge | 8× | — | — | — | $13.35/hr | $1.67/hr | ||
| g6.48xlarge | 8× | — | — | — | $13.35/hr | $1.67/hr | ||
| g6.48xlarge | 8× | — | — | — | $13.35/hr | $1.67/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 L4 right now?
The cheapest current listing is $0.083/hr on Clore.ai, and the median across the 7 providers listing it is $0.80/hr. Running one around the clock for a month (730 hours) at the cheapest rate costs about $61.
What AI models can the Nvidia L4 run?
With 24 GB it runs 7–8B models at FP16, 13–14B at INT8 and about 32B at 4-bit. A 70B model needs a 48 GB card or two 24 GB cards. It can QLoRA fine-tune 7–14B models.
Which models are recommended for the Nvidia L4?
13 models in our catalog have a recommended configuration for this card, with the quantization that fits its 24 GB — see the AI models tab.
Why does the Nvidia L4 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 L4 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
FP16
FP16
INT4
FP16
FP16
INT4
FP16
FP16
FP16
INT4
INT4
Models that run on this GPU.
GPU-count + quantization recommendations covering fine-tuning, inference, and run-it-yourself scenarios on the Nvidia L4.
?
INT4
TheDrummer: Skyfall 36B V2
by Thedrummer
Required GPUs
1× Nvidia L4
Total VRAM
24 GB
Parameters
36B
Context
33K tokens
Whisper Large v3
by OpenAI
Required GPUs
1× Nvidia L4
Total VRAM
24 GB
Parameters
2B
Context
30 tokens
Datacenter STT workhorse.
Whisper Medium
by OpenAI
Required GPUs
1× Nvidia L4
Total VRAM
24 GB
Parameters
1B
Context
30 tokens
Qwen3.6 35B A3b Fp8
by Alibaba (Qwen Team)
Required GPUs
1× Nvidia L4
Total VRAM
24 GB
Parameters
35B
Context
262K tokens
DeepSeek R1 Distill Qwen 7B
by DeepSeek
Required GPUs
1× Nvidia L4
Total VRAM
24 GB
Parameters
8B
Context
128K tokens
Llama 3.2 3B
by Meta AI
Required GPUs
1× Nvidia L4
Total VRAM
24 GB
Parameters
3B
Context
128K tokens
Qwen: Qwen3.5-35B-A3B
by Alibaba (Qwen Team)
Required GPUs
1× Nvidia L4
Total VRAM
24 GB
Parameters
35B
Context
262K tokens
Stable Diffusion XL
by Stability AI
Required GPUs
1× Nvidia L4
Total VRAM
24 GB
Parameters
4B
Llama 3.1 8B
by Meta AI
Required GPUs
1× Nvidia L4
Total VRAM
24 GB
Parameters
8B
Context
128K tokens
Mistral 7B v0.3
by Mistral AI
Required GPUs
1× Nvidia L4
Total VRAM
24 GB
Parameters
7B
Context
33K tokens
Qwen: Qwen3.6 35B A3B
by Alibaba (Qwen Team)
Required GPUs
1× Nvidia L4
Total VRAM
24 GB
Parameters
35B
Context
262K tokens
?
INT4
Holo3 35B A3b
by Hcompany
Required GPUs
1× Nvidia L4
Total VRAM
24 GB
Parameters
35B
Context
262K tokens
LLaVA 34B
by LLaVA Project
Required GPUs
1× Nvidia L4
Total VRAM
24 GB
Parameters
34B
Context
4K 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 L4 right now?
The cheapest current listing is $0.083/hr on Clore.ai, and the median across the 7 providers listing it is $0.80/hr. Running one around the clock for a month (730 hours) at the cheapest rate costs about $61.
What AI models can the Nvidia L4 run?
With 24 GB it runs 7–8B models at FP16, 13–14B at INT8 and about 32B at 4-bit. A 70B model needs a 48 GB card or two 24 GB cards. It can QLoRA fine-tune 7–14B models.
Which models are recommended for the Nvidia L4?
13 models in our catalog have a recommended configuration for this card, with the quantization that fits its 24 GB — see the AI models tab.
Why does the Nvidia L4 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 L4 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.