GPU model · price + stock · hourly snapshot

Nvidia RTX 5090 cloud rental prices

11 providers list the Nvidia RTX 5090, 5 have it in stock. Prices run from $0.39 to $0.82 per GPU hour — the same card, 2.1x apart.

Blackwell 32 GB VRAM Q1 2025 26 configurations

LIVE Prices and stock checked 1 minute ago

Cheapest in stock
$0.39
Median
$0.65
across 11 providers
Most expensive
$0.82
same card, 2.1x the price
You overpay by
39%
if you take the median instead of the floor

Providers

Every provider renting the Nvidia RTX 5090

All providers →
Providers renting the Nvidia RTX 5090, in stock first, then cheapest first
Provider Country Configs Scale From Stock Days in stock Grab
Clore.ai — 2 1x-1x $0.39 In stock 14/14 Grab
OctaSpace — 1 1x-1x $0.41 In stock 14/14 Grab
Vast.ai United States of America 2 2x-2x $0.43 per sec In stock 60/60 Grab
Lium — 1 1x-1x $0.48 In stock 28/28 Grab
SimplePod — 1 1x-1x $0.82 In stock 14/14 Grab
Compshare China 8 1x-8x $0.50 Not reported 0/4 Grab
Meshive — 1 1x-1x $0.68 Not reported 0/4 Grab
Runpod United States of America 1 1x-1x $0.69 per sec Not reported 57/57 Grab
CloudRift United States of America 3 1x-2x $0.65 Out of stock 12/14 Grab
Excess Supply — 5 1x-8x $0.65 Out of stock 42/60 Grab
Phyntec — 1 8x-8x $0.70 Out of stock 2/60 Grab

In stock first, then cheapest. Stock is what the provider reported at our last check. One GPU for a month (730h) at $0.39: $287. Lium publishes live counts: 439 GPUs at $0.48, 83% rented.

Price history

Price trend

Cheapest Nvidia RTX 5090 rate has risen 20.9% since Sep 6 — $0.28 → $0.34/GPU/hr.

$0.341 /GPU/hr · Nov 4

One point per day: the lowest listed $/GPU/hr across every provider we track, captured daily. 360 offers in the latest snapshot.

Configurations

All 26 configurations

26 of 26 configurations
Nvidia RTX 5090 configurations from every provider
ConfigurationProviderRegionVRAMvCPURAMPer GPU/hrTotal/hrStock
2x RTX 5090SpotVast.aiVast.aiCA64 GB44161 GB$0.19per sec$0.38In stock
1x NVIDIA GeForce RTX 5090SpotClore.aiClore.aiUA32 GB—64 GB$0.22$0.22In stock
1x NVIDIA GeForce RTX 5090Clore.aiClore.aiAT32 GB—64 GB$0.39$0.39In stock
1x NVIDIA GeForce RTX 5090OctaSpaceOctaSpaceCA32 GB3262 GB$0.41$0.41In stock
2x RTX 5090Vast.aiVast.aiUS64 GB48126 GB$0.43per sec$0.86In stock
1x NVIDIA GeForce RTX 5090LiumLium————$0.48$0.48In stock
1x RTX 5090SimplePodSimplePodUS32 GB3296 GB$0.82$0.82In stock
1x RTX5090PreemptibleCompshareCompshare—32 GB1448 GB$0.31$0.31Not reported
2x RTX5090PreemptibleCompshareCompshare—64 GB2896 GB$0.31$0.63Not reported
4x RTX5090PreemptibleCompshareCompshare—128 GB56192 GB$0.32$1.26Not reported
8x RTX5090PreemptibleCompshareCompshare—256 GB112480 GB$0.32$2.55Not reported
1x RTX5090CompshareCompshare—32 GB1448 GB$0.50$0.50Not reported
2x RTX5090CompshareCompshare—64 GB2896 GB$0.50$1.01Not reported
4x RTX5090CompshareCompshare—128 GB56192 GB$0.50$2.02Not reported
8x RTX5090CompshareCompshare—256 GB112480 GB$0.53$4.21Not reported
1x RTX 5090CloudRiftCloudRiftap_northeast_kr_se_132 GB1424 GB$0.65$0.65Out of stock
1x RTX5090Excess SupplyExcess Supplyoslo-norway-332 GB12120 GB$0.65$0.65Out of stock
2x RTX5090Excess SupplyExcess Supplyoslo-norway-364 GB24240 GB$0.65$1.30Out of stock
8x RTX5090Excess SupplyExcess Supplyoslo-norway-3256 GB120960 GB$0.65$5.20Out of stock
4x RTX5090Excess SupplyExcess Supplyoslo-norway-3128 GB60480 GB$0.65$2.60Out of stock
1x RTX 5090MeshiveMeshive—32 GB——$0.68$0.68Not reported
1x RTX 5090RunpodRunpod—32 GB——$0.69per sec$0.69Not reported
8x RTX5090Excess SupplyExcess Supplycasper-usa-2256 GB120200 GB$0.70$5.60Out of stock
8x RTX5090PhyntecPhynteccasper-usa-1256 GB64256 GB$0.70$5.60Out of stock
1x RTX 5090CloudRiftCloudRiftna_west_us_gr_132 GB624 GB$0.90$0.90Out of stock
2x RTX 5090CloudRiftCloudRiftna_west_us_gr_164 GB1248 GB$0.90$1.80Out of stock

Model fit

What fits in 32 GB

The question behind most rentals: will the model load. Sized against one Nvidia RTX 5090.

VRAM required to serve open-weight LLMs on a Nvidia RTX 5090, by quantization precision
Model 16-bit8-bit4-bit
DeepSeek-V3 DeepSeek · 671B params · 37B active 1,610 GB 51× · 22 GB free 805 GB 26× · 27 GB free 403 GB 13× · 13 GB free
Llama 3.1 405B Meta · 405B params 972 GB 31× · 20 GB free 486 GB 16× · 26 GB free 243 GB 8× · 13 GB free
Qwen3 235B-A22B Alibaba · 235B params · 22B active 564 GB 18× · 12 GB free 282 GB 9× · 6 GB free 141 GB 5× · 19 GB free
Mixtral 8x22B Mistral · 141B params · 39B active 338 GB 11× · 14 GB free 169 GB 6× · 23 GB free 85 GB 3× · 11 GB free
Mistral Large 2 Mistral · 123B params 295 GB 10× · 25 GB free 148 GB 5× · 12 GB free 74 GB 3× · 22 GB free
gpt-oss-120b OpenAI · 117B params · 5.1B active 281 GB 9× · 7 GB free 140 GB 5× · 20 GB free 70 GB 3× · 26 GB free
Qwen2.5 72B Alibaba · 72.7B params 174 GB 6× · 18 GB free 87 GB 3× · 9 GB free 44 GB 2× · 20 GB free
Llama 3.3 70B Meta · 70.6B params 169 GB 6× · 23 GB free 85 GB 3× · 11 GB free 42 GB 2× · 22 GB free
Qwen3 32B Alibaba · 32.8B params 79 GB 3× · 17 GB free 39 GB 2× · 25 GB free 20 GB 1× · 12 GB free
Gemma 2 27B Google · 27.2B params 65 GB 3× · 31 GB free 33 GB 2× · 31 GB free 16 GB 1× · 16 GB free
Mistral Small 3 Mistral · 24B params 58 GB 2× · 6 GB free 29 GB 1× · 3 GB free 14 GB 1× · 18 GB free
Llama 3.1 8B Meta · 8B params 19 GB 1× · 13 GB free 10 GB 1× · 22 GB free 5 GB 1× · 27 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 RTX 5090.

Specifications

Nvidia RTX 5090 specifications

Nvidia RTX 5090 hardware specifications
ArchitectureBlackwell
Memory per GPU32 GB GDDR7
Memory bandwidth1,792 GB/s
Release dateQ1 2025
FP4 compute rate1,676 TFLOPS (dense), 3,352 with sparsity
FP8 compute rate419 TFLOPS (dense), 838 with sparsity
FP16 / BF16 compute rate209.5 TFLOPS (dense), 419 with sparsity
INT8 compute rate838 TOPS (dense), 1,676 with sparsity
Process nodeTSMC 4N
Board power575 W

Alternatives

Alternatives to the Nvidia RTX 5090

Head to head

Nvidia RTX 5090 head to head