GPU model · price + stock · hourly snapshot

Nvidia RTX A2000 cloud rental prices

1 provider lists the Nvidia RTX A2000, 1 has it in stock. It rents for $0.064 per GPU hour.

Ampere 12 GB VRAM Q3 2021 1 configuration

LIVE Prices and stock checked 1 minute ago

Cheapest in stock
$0.064
Median
$0.064
across 1 provider
Most expensive
$0.064
the only price listed

Providers

Every provider renting the Nvidia RTX A2000

All providers →
Providers renting the Nvidia RTX A2000, in stock first, then cheapest first
Provider Country Configs Scale From Stock Days in stock Grab
OctaSpace — 1 4x-4x $0.064 In stock 11/11 Grab

In stock first, then cheapest. Stock is what the provider reported at our last check. One GPU for a month (730h) at $0.064: $47.

Price history

Price trend

Cheapest Nvidia RTX A2000 rate has fallen 46.3% since Oct 8 — $0.12 → $0.064/GPU/hr.

$0.064 /GPU/hr · Nov 4

One point per day: the lowest listed $/GPU/hr across every provider we track, captured daily. 19 offers in the latest snapshot.

Configurations

The one configuration

1 of 1 configurations
Nvidia RTX A2000 configurations from every provider
ConfigurationProviderRegionVRAMvCPURAMPer GPU/hrTotal/hrStock
4x NVIDIA RTX A2000 12GBOctaSpaceOctaSpaceAR47 GB28 GB$0.06$0.26In stock

Model fit

What fits in 12 GB

The question behind most rentals: will the model load. Sized against one Nvidia RTX A2000.

VRAM required to serve open-weight LLMs on a Nvidia RTX A2000, by quantization precision
Model 16-bit8-bit4-bit
DeepSeek-V3 DeepSeek · 671B params · 37B active 1,610 GB 135× · 10 GB free 805 GB 68× · 11 GB free 403 GB 34× · 5 GB free
Llama 3.1 405B Meta · 405B params 972 GB 81× · 0 GB free 486 GB 41× · 6 GB free 243 GB 21× · 9 GB free
Qwen3 235B-A22B Alibaba · 235B params · 22B active 564 GB 47× · 0 GB free 282 GB 24× · 6 GB free 141 GB 12× · 3 GB free
Mixtral 8x22B Mistral · 141B params · 39B active 338 GB 29× · 10 GB free 169 GB 15× · 11 GB free 85 GB 8× · 11 GB free
Mistral Large 2 Mistral · 123B params 295 GB 25× · 5 GB free 148 GB 13× · 8 GB free 74 GB 7× · 10 GB free
gpt-oss-120b OpenAI · 117B params · 5.1B active 281 GB 24× · 7 GB free 140 GB 12× · 4 GB free 70 GB 6× · 2 GB free
Qwen2.5 72B Alibaba · 72.7B params 174 GB 15× · 6 GB free 87 GB 8× · 9 GB free 44 GB 4× · 4 GB free
Llama 3.3 70B Meta · 70.6B params 169 GB 15× · 11 GB free 85 GB 8× · 11 GB free 42 GB 4× · 6 GB free
Qwen3 32B Alibaba · 32.8B params 79 GB 7× · 5 GB free 39 GB 4× · 9 GB free 20 GB 2× · 4 GB free
Gemma 2 27B Google · 27.2B params 65 GB 6× · 7 GB free 33 GB 3× · 3 GB free 16 GB 2× · 8 GB free
Mistral Small 3 Mistral · 24B params 58 GB 5× · 2 GB free 29 GB 3× · 7 GB free 14 GB 2× · 10 GB free
Llama 3.1 8B Meta · 8B params 19 GB 2× · 5 GB free 10 GB 1× · 2 GB free 5 GB 1× · 7 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 A2000.

Specifications

Nvidia RTX A2000 specifications

Nvidia RTX A2000 hardware specifications
ArchitectureAmpere
Memory per GPU12 GB GDDR6
Memory bandwidth288 GB/s
Release dateQ3 2021
FP16 / BF16 compute rate31.9 TFLOPS (dense), 63.9 with sparsity
Board power70 W

Alternatives

Alternatives to the Nvidia RTX A2000