GPU model · price + stock · hourly snapshot

Nvidia A40 cloud rental prices

4 providers list the Nvidia A40, 2 have it in stock. Prices run from $0.47 to $1.86 per GPU hour — the same card, 4.0x apart.

Ampere 48 GB VRAM Q4 2020 25 configurations

LIVE Prices and stock checked 1 minute ago

Cheapest in stock
$0.47
Median
$0.84
across 4 providers
Most expensive
$1.86
same card, 4.0x the price
You overpay by
45%
if you take the median instead of the floor

Providers

Every provider renting the Nvidia A40

All providers →
Providers renting the Nvidia A40, in stock first, then cheapest first
Provider Country Configs Scale From Stock Days in stock Grab
Vast.ai United States of America 2 2x-4x $0.47 per sec In stock 55/55 Grab
Vultr United States of America 18 1x-4x $1.86 In stock 41/60 Grab
Runpod United States of America 1 1x-1x $0.59 per sec Not reported 53/54 Grab
Crusoe United States of America 4 1x-8x $1.10 Out of stock 0/60 Grab

In stock first, then cheapest. Stock is what the provider reported at our last check. One GPU for a month (730h) at $0.47: $341.

Price history

Price trend

Cheapest Nvidia A40 rate has fallen 23.0% since Sep 6 — $0.35 → $0.27/GPU/hr.

$0.270 /GPU/hr · Nov 4

One point per day: the lowest listed $/GPU/hr across every provider we track, captured daily. 432 offers in the latest snapshot.

Configurations

All 25 configurations

25 of 25 configurations
Nvidia A40 configurations from every provider
ConfigurationProviderRegionVRAMvCPURAMPer GPU/hrTotal/hrStock
2x A40SpotVast.aiVast.aiBE90 GB1281002 GB$0.16per sec$0.32In stock
4x A40Vast.aiVast.aiBE180 GB2562004 GB$0.47per sec$1.87In stock
1x A40VultrVultrlosangeles-usa-148 GB24120 GB$1.86$1.86In stock
1x A40RunpodRunpod—48 GB——$0.59per sec$0.59Not reported
1x A40CrusoeCrusoefairview-usa-148 GB660 GB$1.10$1.10Out of stock
4x A40CrusoeCrusoefairview-usa-1192 GB24240 GB$1.10$4.40Out of stock
2x A40CrusoeCrusoefairview-usa-196 GB12120 GB$1.10$2.20Out of stock
8x A40CrusoeCrusoefairview-usa-1384 GB48480 GB$1.10$8.80Out of stock
1x A40VultrVultrfrankfurt-germany-648 GB24120 GB$1.86$1.86Out of stock
1x A40VultrVultrtokyo-japan-248 GB24120 GB$1.86$1.86Out of stock
1x A40VultrVultrsanjose-usa-148 GB24120 GB$1.86$1.86Out of stock
1x A40VultrVultrsydney-australia-148 GB24120 GB$1.86$1.86Out of stock
1x A40VultrVultrbangalore-india-148 GB24120 GB$1.86$1.86Out of stock
1x A40VultrVultrlondon-uk-148 GB24120 GB$1.86$1.86Out of stock
1x A40VultrVultrsingapore-singapore-148 GB24120 GB$1.86$1.86Out of stock
1x A40VultrVultrnewark-usa-148 GB24120 GB$1.86$1.86Out of stock
4x A40VultrVultrbangalore-india-1192 GB96480 GB$1.86$7.44Out of stock
4x A40VultrVultrtokyo-japan-2192 GB96480 GB$1.86$7.44Out of stock
4x A40VultrVultrsanjose-usa-1192 GB96480 GB$1.86$7.44Out of stock
4x A40VultrVultrlondon-uk-1192 GB96480 GB$1.86$7.44Out of stock
4x A40VultrVultrnewark-usa-1192 GB96480 GB$1.86$7.44Out of stock
4x A40VultrVultrfrankfurt-germany-6192 GB96480 GB$1.86$7.44Out of stock
4x A40VultrVultrsydney-australia-1192 GB96480 GB$1.86$7.44Out of stock
4x A40VultrVultrlosangeles-usa-1192 GB96480 GB$1.86$7.44Out of stock
4x A40VultrVultrsingapore-singapore-1192 GB96480 GB$1.86$7.44Out of stock

Model fit

What fits in 48 GB

The question behind most rentals: will the model load. Sized against one Nvidia A40.

VRAM required to serve open-weight LLMs on a Nvidia A40, by quantization precision
Model 16-bit8-bit4-bit
DeepSeek-V3 DeepSeek · 671B params · 37B active 1,610 GB 34× · 22 GB free 805 GB 17× · 11 GB free 403 GB 9× · 29 GB free
Llama 3.1 405B Meta · 405B params 972 GB 21× · 36 GB free 486 GB 11× · 42 GB free 243 GB 6× · 45 GB free
Qwen3 235B-A22B Alibaba · 235B params · 22B active 564 GB 12× · 12 GB free 282 GB 6× · 6 GB free 141 GB 3× · 3 GB free
Mixtral 8x22B Mistral · 141B params · 39B active 338 GB 8× · 46 GB free 169 GB 4× · 23 GB free 85 GB 2× · 11 GB free
Mistral Large 2 Mistral · 123B params 295 GB 7× · 41 GB free 148 GB 4× · 44 GB free 74 GB 2× · 22 GB free
gpt-oss-120b OpenAI · 117B params · 5.1B active 281 GB 6× · 7 GB free 140 GB 3× · 4 GB free 70 GB 2× · 26 GB free
Qwen2.5 72B Alibaba · 72.7B params 174 GB 4× · 18 GB free 87 GB 2× · 9 GB free 44 GB 1× · 4 GB free
Llama 3.3 70B Meta · 70.6B params 169 GB 4× · 23 GB free 85 GB 2× · 11 GB free 42 GB 1× · 6 GB free
Qwen3 32B Alibaba · 32.8B params 79 GB 2× · 17 GB free 39 GB 1× · 9 GB free 20 GB 1× · 28 GB free
Gemma 2 27B Google · 27.2B params 65 GB 2× · 31 GB free 33 GB 1× · 15 GB free 16 GB 1× · 32 GB free
Mistral Small 3 Mistral · 24B params 58 GB 2× · 38 GB free 29 GB 1× · 19 GB free 14 GB 1× · 34 GB free
Llama 3.1 8B Meta · 8B params 19 GB 1× · 29 GB free 10 GB 1× · 38 GB free 5 GB 1× · 43 GB free

Required memory is weights plus 20% for KV cache and runtime at short context; long contexts and large batches need more. Cells tinted green fit on a single Nvidia A40.

Specifications

Nvidia A40 specifications

Nvidia A40 hardware specifications
ArchitectureAmpere
Memory per GPU48 GB GDDR6
Memory bandwidth696 GB/s
Release dateQ4 2020
FP16 / BF16 compute rate149.7 TFLOPS (dense), 299.4 with sparsity
INT8 compute rate299.3 TOPS (dense), 598.6 with sparsity
Process nodeSamsung 8N
Board power300 W

Alternatives

Alternatives to the Nvidia A40