datacenter
Nvidia A2 mieten.
Ampere
16GB VRAM
60W
From $0.29/hr
Per hour
$0.29
Per day
$7.00
Per week
$49.01
Per month
$210
Price history
Daily median across providers.
Loading...
Where to rent it
All providers carrying this GPU.
Buy vs rent
Should you rent or own?
Your usage
Rent on cloud
Per day
—
Per month
—
at $0.29/hr cheapest provider rate
Own on-prem
Electricity per day
—
60W TDP
Rent breakeven on $1,500 MSRP
— days
· — months
FAQ
Frequently asked.
How much does it cost to rent the Nvidia A2 right now?
The cheapest current listing is $0.29/hr on Clore.ai, the only provider listing it right now. Running one around the clock for a month (730 hours) at the cheapest rate costs about $213.
What AI models can the Nvidia A2 run?
With 16 GB it runs 7–8B models at INT8 (or FP16 with short contexts) and 13–14B at 4-bit. It suits single-model inference, embeddings and QLoRA fine-tuning of 7B models.
Which models are recommended for the Nvidia A2?
6 models in our catalog have a recommended configuration for this card, with the quantization that fits its 16 GB — see the AI models tab.
Why does the Nvidia A2 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 A2 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
Models that run on this GPU.
GPU-count + quantization recommendations covering fine-tuning, inference, and run-it-yourself scenarios on the Nvidia A2.
LFM2-24B-A2B
by Togethercomputer
Required GPUs
1× Nvidia A2
Total VRAM
16 GB
Parameters
24B
Context
33K tokens
Sarvam M
by Sarvamai
Required GPUs
1× Nvidia A2
Total VRAM
16 GB
Parameters
24B
Context
33K tokens
?
INT4
TheDrummer: Cydonia 24B V4.1
by Thedrummer
Required GPUs
1× Nvidia A2
Total VRAM
16 GB
Parameters
24B
Context
131K tokens
Mistral: Mistral Small 3.2 24B
by Mistral AI
Required GPUs
1× Nvidia A2
Total VRAM
16 GB
Parameters
24B
Context
128K tokens
Mistral: Mistral Small 3.1 24B
by Mistral AI
Required GPUs
1× Nvidia A2
Total VRAM
16 GB
Parameters
24B
Context
128K tokens
Mistral: Mistral Small 3
by Mistral AI
Required GPUs
1× Nvidia A2
Total VRAM
16 GB
Parameters
24B
Context
33K 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 A2 right now?
The cheapest current listing is $0.29/hr on Clore.ai, the only provider listing it right now. Running one around the clock for a month (730 hours) at the cheapest rate costs about $213.
What AI models can the Nvidia A2 run?
With 16 GB it runs 7–8B models at INT8 (or FP16 with short contexts) and 13–14B at 4-bit. It suits single-model inference, embeddings and QLoRA fine-tuning of 7B models.
Which models are recommended for the Nvidia A2?
6 models in our catalog have a recommended configuration for this card, with the quantization that fits its 16 GB — see the AI models tab.
Why does the Nvidia A2 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 A2 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.