Nvidia RTX 3080

Nvidia RTX 3080

Ampere consumer GPU for local AI experimentation.

Compare vs other GPUs →
Aggregating historical prices...

Key Specifications

Architecture
Ampere
Memory
10GB GDDR6X
Memory Bandwidth
760 GB/s
Release date
Q3 2020

Compare Cloud Provider Prices

Barriers to entry are low here. 4 cloud providers list the RTX 3080 with prices starting at just $0.07/hr per GPU (spot instance), making it accessible for testing without a large commitment.

of shown

Default ranking

Our algorithm weighs five factors to find the most relevant matches for you:

  1. Price: We blend total hourly price with price-per-GPU to balance affordability and value.
  2. Specs: We favor offers with higher CPU, RAM, and GPU Memory.
  3. Billing: We favor on-demand billing for simplicity and flexibility over spot instances, reservations, and custom quotes.
  4. Location: We blend both datacenter proximity and provider HQ location. Datacenter location matters for latency, while HQ location matters for compliance and support.
  5. Provider diversity: Each time a provider appears in the list, their subsequent offerings are ranked a little lower, so one provider's offerings don't crowd out the top positions.

Sorting and filtering

Click any column header to sort by that column. Use the filters above the table to narrow results by billing type, GPU count, vCPUs, or RAM. Custom sorting resets the default relevance ranking.

Transparency and funding

Ads and sponsors: Any paid placements are fixed at the top and clearly labeled as sponsored content.

Affiliates: Any affiliate links will be indicated to you as well. We may earn a commission if you click them, but this never influences the ranking order.

Provider GPUs Total VRAM vCPUs RAM Billing $/GPU/h Total/h Availability
Theta EdgeCloud logo Theta EdgeCloud 1x RTX 3080 1x RTX 3080 10GB 10GB 44 62GB On-Demand Pay-as-you-go pricing. No term commitments. $0.17 $0.17 Available View
Runpod logo Runpod 1x RTX 3080 1x RTX 3080 10GB (community-cloud) 10GB 6 16GB On-Demand Pay-as-you-go pricing. No term commitments. $0.17 $0.17 Available View
Salad logo Salad 1x RTX 3080 1x RTX 3080 10GB (RTX 3080) 10GB 4 8GB On-Demand Pay-as-you-go pricing. No term commitments. $0.08 $0.08 Available View
Vast.ai logo Vast.ai 1x RTX 3080 1x RTX 3080 10GB (35401045) 10GB 64 14GB On-Demand Pay-as-you-go pricing. No term commitments. $0.12 $0.12 Available View
Vast.ai logo Vast.ai 2x RTX 3080 2x RTX 3080 10GB (36503268) 20GB 64 32GB On-Demand Pay-as-you-go pricing. No term commitments. $0.11 $0.22 Available View
Vast.ai logo Vast.ai 2x RTX 3080 2x RTX 3080 10GB (35401051) 20GB 64 28GB On-Demand Pay-as-you-go pricing. No term commitments. $0.12 $0.24 Available View
Vast.ai logo Vast.ai 1x RTX 3080 1x RTX 3080 10GB (30703387) 10GB 4 5GB On-Demand Pay-as-you-go pricing. No term commitments. $0.18 $0.18 Available View
Vast.ai logo Vast.ai 1x RTX 3080 1x RTX 3080 10GB (37741263) 10GB 10 15GB On-Demand Pay-as-you-go pricing. No term commitments. $0.19 $0.19 Available View
Vast.ai logo Vast.ai 1x RTX 3080 1x RTX 3080 10GB (35935336) 10GB 6 32GB On-Demand Pay-as-you-go pricing. No term commitments. $0.21 $0.21 Available View
Vast.ai logo Vast.ai 1x RTX 3080 1x RTX 3080 10GB (37501852) 10GB 12 16GB On-Demand Pay-as-you-go pricing. No term commitments. $0.22 $0.22 Available View
Vast.ai logo Vast.ai 1x RTX 3080 1x RTX 3080 10GB (35948065) 10GB 24 32GB On-Demand Pay-as-you-go pricing. No term commitments. $0.24 $0.24 Available View
Vast.ai logo Vast.ai 4x RTX 3080 4x RTX 3080 10GB (35401057) 40GB 64 56GB On-Demand Pay-as-you-go pricing. No term commitments. $0.12 $0.48 Available View
Vast.ai logo Vast.ai 2x RTX 3080 2x RTX 3080 10GB (35401051) 20GB 64 28GB Spot Variable spot pricing with potential interruptions. $0.07 $0.14 Available View
Vast.ai logo Vast.ai 2x RTX 3080 2x RTX 3080 10GB (35948062) 20GB 24 64GB On-Demand Pay-as-you-go pricing. No term commitments. $0.24 $0.48 Available View
Vast.ai logo Vast.ai 2x RTX 3080 2x RTX 3080 10GB (36503268) 20GB 64 32GB Reserved (6mo) Reserved capacity with a 6-month minimum commitment. $0.11 $0.22 Available View
Vast.ai logo Vast.ai 2x RTX 3080 2x RTX 3080 10GB (36503268) 20GB 64 32GB Spot Variable spot pricing with potential interruptions. $0.09 $0.19 Available View
Vast.ai logo Vast.ai 4x RTX 3080 4x RTX 3080 10GB (35401057) 40GB 64 56GB Spot Variable spot pricing with potential interruptions. $0.07 $0.27 Available View
Vast.ai logo Vast.ai 1x RTX 3080 1x RTX 3080 10GB (35935336) 10GB 6 32GB Spot Variable spot pricing with potential interruptions. $0.15 $0.15 Available View
Vast.ai logo Vast.ai 1x RTX 3080 1x RTX 3080 10GB (35948065) 10GB 24 32GB Spot Variable spot pricing with potential interruptions. $0.16 $0.16 Available View
No offerings matching your filters.

Heads up: We do our best to keep these prices accurate. However, cloud costs may fluctuate based on region, usage, and other factors not listed here. These are estimates based on common setups and are for informational purposes only. Always verify current rates with the provider before provisioning.

Frequently Asked Questions

Why choose the RTX 3080?

10GB or 12GB GDDR6X with Ampere Tensor Cores. Budget option for local AI experimentation.

When is the RTX 3080 not a good fit?

10-12GB VRAM limits model sizes. No FP8. Subject to Nvidia's consumer EULA, which may restrict data center use.

Are RTX 3080 prices going up or down?

On-demand pricing has increased by about 163% since July 2025, from $0.11 to $0.29/hr per GPU.

What size AI models can the RTX 3080 run?

With 10GB of VRAM, the RTX 3080 is mainly limited to small quantized models and lightweight GPU workloads.

How much VRAM does the RTX 3080 have?

The RTX 3080 has 10GB of VRAM. Multi-GPU setups increase total memory, but that memory is not automatically pooled across GPUs.

What is the RTX 3080's memory bandwidth?

The RTX 3080 has 760 GB/s of memory bandwidth. Higher bandwidth helps with faster data transfer between GPU memory and compute cores.

What data types does the RTX 3080 support?

The RTX 3080 supports 5 precision formats. Training: BF16, FP16, TF32, FP32. Inference: INT8.

Does the RTX 3080 support NVLink?

No. The RTX 3080 is a PCIe-only GPU with no NVLink, so it is better suited to single-GPU inference and smaller-scale workloads than large distributed training jobs.

How much does the RTX 3080 cost per hour?

RTX 3080 pricing currently ranges from $0.07/hr to $0.24/hr per GPU, depending on the provider, instance type, and billing model.

How much does the RTX 3080 cost per month?

At 720 hours per month, one RTX 3080 can cost between $48.44 to $172.87 per month, depending on the provider. Reserved and spot pricing can lower that further.

Which cloud providers offer the RTX 3080?

The RTX 3080 is available from 4 cloud providers, including Runpod, Salad, Theta EdgeCloud. Pricing and availability vary by region and billing model.

Can I rent the RTX 3080 in the cloud?

Yes. We currently track 24 RTX 3080 listings across 4 cloud providers:

Billing type Listings Avg $/GPU/hr
On-demand 14 $0.16/hr
Reserved 2 $0.16/hr
Spot 8 $0.10/hr

Technical Specifications

Architecture Ampere
CUDA Cores 8704
Memory Size 10 GB
Memory Type GDDR6X
Memory Bandwidth 760.3 GB/s
TDP 320W

Source: official Nvidia RTX 3080 datasheet.

Alternatives to Nvidia RTX 3080

Last updated