← Back to all offerings

RTX 3080

10 GB VRAM320 W TDP2 providers4 offerings2 regions

The RTX 3080 is a cloud GPU with 10 GB of memory and 320 W TDP. It is currently available from 2 providers starting at $0.10/hr, with a market median of $0.26/hr across 4 offerings.

$0.10/hr
Cheapest
on HardwareHQ
$0.26/hr
Median
across 4 offerings
$1.11/hr
Most expensive
+1100.0%
90-day trend

Best deal

Hardware specifications

Architecture
Ampere
VRAM
10 GB
Memory type
GDDR6X
Memory bandwidth
760 GB/s
FP32
30 TFLOPS
TDP
320 W

Same across all providers.

Market comparison

$0.26/hr
Our median / hr
$0.16/hr
gpus.io median / hr
4
Our providers
3
gpus.io providers

View source on gpus.io

All-time price history

Offerings

All ×N×1×2×4×8In stock only · Partners only
ProviderCloudCountvCPURAMRegionPer GPU hrSPOTTotal/hr
HardwareHQ
0.0% 30dReferral link
×2126 GBMX$0.05/hr$0.10/hrLaunch ↗
HardwareHQ
0.0% 30dReferral link
×2$0.17/hr$0.34/hrLaunch ↗

LLMs that fit

ModelParams16-bit8-bit4-bit
Llama 3.1 70B
Meta
70BNeeds >8 GPUsNeeds >8 GPUsBarely fits on 6×
Qwen3.6 35B-A3B
Alibaba
35B 3B activeNeeds >8 GPUsBarely fits on 6×4× · 6.4 GB free
Qwen3 32B
Alibaba
32.8BNeeds >8 GPUs6× · 14% spareBarely fits on 3×
Qwen2.5 14B
Alibaba
14BBarely fits on 4×Barely fits on 2×2× · 8.6 GB free
Llama 3.1 8B
Meta
8B3× · 9.1 GB free2× · 8.6 GB free1× · 3.3 GB free
Mistral 7B
Mistral AI
7BBarely fits on 2×Barely fits on 1×1× · 4.1 GB free
Qwen3 4B
Alibaba
4B2× · 8.4 GB free1× · 3.6 GB free1× · 6.3 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.

Similar GPUs

Frequently asked questions

How much does the RTX 3080 cost per hour?

The cheapest RTX 3080 offering starts at $0.10/hr, and the market median is $0.26/hr.

Which cloud providers offer the RTX 3080?

We track RTX 3080 offerings from HardwareHQ.

How much VRAM does the RTX 3080 have?

The RTX 3080 has 10 GB of VRAM.

What LLMs can run on the RTX 3080?

With 10 GB of VRAM, the RTX 3080 can run 7 of our tracked models in 4-bit quantization, including Qwen3.6 35B-A3B, Qwen3 32B, Llama 3.1 70B. 4 models fit in 16-bit precision.

What's the biggest LLM I can run on multiple RTX 3080s?

With 8× RTX 3080 (80 GB total), the largest tracked model that fits in 16-bit is Llama 3.1 8B (8B params), which needs 3× GPUs.

Where is the RTX 3080 cheapest?

The cheapest RTX 3080 offering in our catalog is HardwareHQ at $0.05/hr per GPU-hour (×2).