grab▲gpu

GPU model · price + stock · hourly snapshot

Nvidia P4 cloud rental prices

1 provider lists the Nvidia P4, 1 has it in stock. It rents for $0.035 per GPU hour.

Pascal 8 GB VRAM Q3 2016 2 configurations

LIVE Prices and stock checked 1 minute ago

Cheapest in stock
$0.035
Clore.ai
Median
$0.035
across 1 provider
Most expensive
$0.035
the only price listed

Providers

Every provider renting the Nvidia P4

All providers →

Billing:

On-demandfrom $0.035/hr1 provider in stockPay as you go, stop any time.Spotfrom $0.026/hr1 provider in stockCheaper, but the provider can take the machine back.Reservednone listedPrepay a term for the lowest hourly rate.
Providers renting the Nvidia P4, in stock first, then cheapest first
Provider Country Configs Scale From Stock Days in stock Grab
Clore.ai — 2 1x-1x $0.035 In stock 7/7 Grab

In stock first, then cheapest. Stock is what the provider reported at our last check. One GPU for a month (730h) at $0.035: $25.

Price history

Price trend

Cheapest Nvidia P4 rate has held at $0.017/GPU/hr since Oct 27.

$0.017 /GPU/hr · Nov 4

One point per day: the lowest listed $/GPU/hr across every provider we track, captured daily. 13 offers in the latest snapshot.

Configurations

All 2 configurations

2 of 2 configurations
Nvidia P4 configurations from every provider
ConfigurationProviderRegionVRAMvCPURAMPer GPU/hrTotal/hrStock
1x Tesla P4SpotClore.aiClore.aiUS8 GB—32 GB$0.03$0.03In stock
1x Tesla P4Clore.aiClore.aiUS8 GB—32 GB$0.03$0.03In stock

Model fit

What fits in 8 GB

The question behind most rentals: will the model load. Sized against one Nvidia P4.

VRAM required to serve open-weight LLMs on a Nvidia P4, by quantization precision
Model 16-bit8-bit4-bit
DeepSeek-V3 DeepSeek · 671B params · 37B active 1,610 GB 202× · 6 GB free 805 GB 101× · 3 GB free 403 GB 51× · 5 GB free
Llama 3.1 405B Meta · 405B params 972 GB 122× · 4 GB free 486 GB 61× · 2 GB free 243 GB 31× · 5 GB free
Qwen3 235B-A22B Alibaba · 235B params · 22B active 564 GB 71× · 4 GB free 282 GB 36× · 6 GB free 141 GB 18× · 3 GB free
Mixtral 8x22B Mistral · 141B params · 39B active 338 GB 43× · 6 GB free 169 GB 22× · 7 GB free 85 GB 11× · 3 GB free
Mistral Large 2 Mistral · 123B params 295 GB 37× · 1 GB free 148 GB 19× · 4 GB free 74 GB 10× · 6 GB free
gpt-oss-120b OpenAI · 117B params · 5.1B active 281 GB 36× · 7 GB free 140 GB 18× · 4 GB free 70 GB 9× · 2 GB free
Qwen2.5 72B Alibaba · 72.7B params 174 GB 22× · 2 GB free 87 GB 11× · 1 GB free 44 GB 6× · 4 GB free
Llama 3.3 70B Meta · 70.6B params 169 GB 22× · 7 GB free 85 GB 11× · 3 GB free 42 GB 6× · 6 GB free
Qwen3 32B Alibaba · 32.8B params 79 GB 10× · 1 GB free 39 GB 5× · 1 GB free 20 GB 3× · 4 GB free
Gemma 2 27B Google · 27.2B params 65 GB 9× · 7 GB free 33 GB 5× · 7 GB free 16 GB 3× · 8 GB free
Mistral Small 3 Mistral · 24B params 58 GB 8× · 6 GB free 29 GB 4× · 3 GB free 14 GB 2× · 2 GB free
Llama 3.1 8B Meta · 8B params 19 GB 3× · 5 GB free 10 GB 2× · 6 GB free 5 GB 1× · 3 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 P4.

Specifications

Nvidia P4 specifications

Nvidia P4 hardware specifications
ArchitecturePascal
Memory per GPU8 GB GDDR5
Memory bandwidth192 GB/s
Release dateQ3 2016
INT8 compute rate22 TOPS (dense)
Process nodeTSMC 16nm FinFET
Board power75 W

Alternatives

Alternatives to the Nvidia P4