datacenter

Louer NVIDIA A40.

Name: NVIDIA A40
Brand: Nvidia
SKU: nvidia-a40

Ampere 48GB VRAM From $0.32/hr

Per hour

$0.32

Per day

$7.64

Per week

$53.46

Per month

$229

Provider spread 2 providers · up to 9% cheaper at the low end

Cheapest · $0.32/hr on Nosana Median $0.33/hr Most expensive · $0.35/hr on RunPod

Price history

Daily median across providers.

Where to rent it

All providers carrying this GPU.

Provider	$/hr	Range	Offers	30d trend	Updated
Nosana	$0.32/hr	$0.27/hr–$0.36/hr	2	·	3 minutes
RunPod	$0.35/hr	$0.35/hr–$0.35/hr	1	·	4 minutes	Launch ↗

AI models that fit See all 53 →

Run these on this GPU.

Qwen 2.5 72B 1× · int4
Llama 4 Scout 17B 16E Instruct Fp8 Lora 1× · fp16
Llama 4 Maverick Instruct (17Bx128E) FP8 1× · fp16

FAQ

Frequently asked.

How much does it cost to rent the NVIDIA A40 right now?

The cheapest current listing is $0.32/hr on Nosana, and the median across the 2 providers listing it is $0.35/hr. Running one around the clock for a month (730 hours) at the cheapest rate costs about $232.

What AI models can the NVIDIA A40 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 A40?

53 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 A40 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 A40 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.

Louer NVIDIA A40.

Daily median across providers.

All providers carrying this GPU.

Run these on this GPU.

Frequently asked.

Models that run on this GPU.

Qwen 2.5 72B

Llama 4 Scout 17B 16E Instruct Fp8 Lora

Llama 4 Maverick Instruct (17Bx128E) FP8

Llama 4 Scout (17Bx16E)

Llama 4 Scout Instruct (17Bx16E)

Qwen2.5 72B Instruct

Qwen2 72B Instruct

Qwen2.5 72B Instruct Turbo

Qwen2-VL (72B) Instruct

Qwen: Qwen2.5 VL 72B Instruct

Qwen 2.5 Coder 32B

DeepSeek R1 Distill Qwen 32B

Qwen 2.5 32B

Qwen 3 32B

LLaVA 34B

Code Llama 34B

DeepSeek Coder 33B

Yi-34B

Qwen: Qwen3.6 35B A3B

Qwen: Qwen3.5-35B-A3B

TheDrummer: Skyfall 36B V2

Holo3 35B A3b

Deepseek Coder 33B Instruct

Qwen3.6 35B A3b Fp8

Llama 3.3 70B

DeepSeek R1 Distill Llama 70B

Llama 3.1 70B

Code Llama 70B

Hermes 3 70B

Nous: Hermes 4 70B

Sao10K: Llama 3.1 70B Hanami x1

Sao10K: Llama 3.3 Euryale 70B

Magnum v4 72B

Sao10K: Llama 3.1 Euryale 70B v2.2

Sao10k: Llama 3 Euryale 70B v2.1

Meta: Llama 3 70B Instruct

Meta Llama 3.3 70B Instruct Turbo

Meta Llama 3.1 70B Instruct Turbo

nim/meta/llama-3.1-70b-instruct

nim/nvidia/llama-3.1-nemotron-70b-instruct

Cogito V1 Preview Llama 70B

Cogito V1 Preview Llama 70B Turbo

Qwen 2 (72B)

Qwen2.5 72B

Llama 3.1 70B

Meta Llama 3 70B Instruct Turbo

nim/meta/llama-3.3-70b-instruct

Llama 3.1 Nemotron 70B Instruct HF

meta-llama/Llama-3.3-70B-Instruct

Llama 3.3 70B Instruct FP8 Lora

Hermes-3-Llama-3.1-70B

L3.1-70B-Euryale-v2.2

Meta-Llama-3.1-70B-Instruct

AI models on this GPU.