Back to all offerings

NVIDIA Quadro P2000

5 GB VRAM75 W TDP2 providers3 offerings2 regions

The NVIDIA Quadro P2000 is an enterprise-class GPU built on the Pascal architecture, featuring 5 GB of memory with 140 GB/s of memory bandwidth and a 75 W TDP. It delivers 3 TFLOPS of FP32 performance. Currently available from 2 providers starting at $0.03/GPU/hour, with a market median of $0.03/GPU/hour across 3 configurations.

Cheapest
$0.030/hr
Vast.ai
Median
$0.030/hr
across 3 offerings
Most expensive
$0.250/hr
Akash Network
90-day trend
0.0%
median rate

Hardware specifications

Same across all providers

TDP
75 W
Memory bandwidth
140 GB/s
Architecture
Pascal
FP32 performance
3 TFLOPS
Brand
NVIDIA
Series
Quadro
Market price history

Median price across all providers

Prices updated 1 hour ago

2 offerings from 2 providers

Sorted by price ascending. Compare configurations side-by-side.

ProviderCountvCPURAMRegionPer GPU hourTotal/hrAction
Vast.ai logoVast.aiReferral linkTrendingCheapest
×157 GB
United States
$0.030
0.0% 30d
From$0.03
Launch
Up to$100credit
×1
Switzerland
$0.250
-16.7% 30d
$0.25
Launch

LLMs that fit on the NVIDIA Quadro P2000

Estimated VRAM for popular open-weight LLMs at 16-bit (FP16/BF16), 8-bit (FP8/INT8) and 4-bit (INT4/MXFP4) precision, against 5 GB per GPU.

ModelParameters16-bit8-bit4-bit
Gemma 3 12B
Google
12.2B
29 GB
Too large
16 GB
Too large
9.4 GB
Barely fits on 2×
Granite 4.1 8B
IBM
8.8B
21 GB
Too large
12 GB
Tight on 2× · 3% spare
6.8 GB
2× · 3.2 GB free
Qwen3 8B
Alibaba
8.2B
20 GB
Too large
11 GB
Tight on 2× · 10% spare
6.3 GB
2× · 3.7 GB free
Llama 3.1 8B Instruct
Meta
8B
19 GB
Too large
11 GB
Tight on 2× · 13% spare
6.2 GB
2× · 3.8 GB free
Mistral 7B Instruct v0.3
Mistral AI
7.2B
17 GB
Too large
9.6 GB
Barely fits on 2×
5.6 GB
2× · 4.4 GB free
or 1× · 7% spare
Qwen3 4B
Alibaba
4B
9.7 GB
Barely fits on 2×
5.3 GB
2× · 4.7 GB free
or 1× · 13% spare
3.1 GB
1× · 1.9 GB free

Estimates: model weights plus 20% for KV cache and runtime overhead, at short context lengths. Long contexts and large batches need more. Rows marked “tight” hold the weights but not that full margin. A ×N figure is the total VRAM across N of these GPUs and makes no claim about interconnect throughput. How we estimate this · Start from a model instead

Want more from this page?

See incorrect data?

Frequently asked questions

How much does the Quadro P2000 cost per hour?
The Quadro P2000 starts at $0.03 per GPU-hour, with a median of $0.03 across 3 available configurations. Actual pricing depends on the provider, region, and whether you rent on-demand, spot or reserved.
Which cloud providers offer the Quadro P2000?
2 providers currently list the Quadro P2000: Akash Network, Vast.ai. Compare their hourly pricing, regions and machine specs in the table above.
How much VRAM does the Quadro P2000 have?
The Quadro P2000 comes with 5 GB of VRAM, which determines the largest models and batch sizes it can hold in memory for training and inference.
Which LLMs can I run on the Quadro P2000?
With 5 GB of VRAM, a single Quadro P2000 can serve models such as Qwen3 4B. The table above lists the estimated VRAM for each model at 16-bit, 8-bit and 4-bit precision, including the multi-GPU configurations needed for larger models.
What's the biggest LLM I can run on multiple Quadro P2000 GPUs?
The largest models we track that fit across several Quadro P2000 cards are Gemma 3 12B on 2 GPUs at 4-bit, Granite 4.1 8B on 2 GPUs at 4-bit, Qwen3 8B on 2 GPUs at 4-bit. A multi-GPU configuration means you rent and pay for every card for the whole run, and splitting a model across cards costs throughput as well: the GPUs exchange activations on every token, so performance depends on how fast they are wired together. We do not track interconnect, so check the provider's node specification. The table above gives the smallest configuration for each model at 16-bit, 8-bit and 4-bit precision.
Where is the Quadro P2000 cheapest?
The lowest on-demand price we currently track for the Quadro P2000 is $0.03 per GPU-hour at Vast.ai. Because providers update pricing and availability frequently, check the live table above before you launch.