Nvidia A10
Balanced cloud GPU for inference and graphics at a moderate price point.
Compare vs other GPUs →Key Specifications
Compare Cloud Provider Prices
Barriers to entry are low here. 10 cloud providers list the A10 with prices starting at just $0.09/hr per GPU (spot instance), making it accessible for testing without a large commitment.
How we sort results
Default ranking
Our algorithm weighs five factors to find the most relevant matches for you:
- Price: We blend total hourly price with price-per-GPU to balance affordability and value.
- Specs: We favor offers with higher CPU, RAM, and GPU Memory.
- Billing: We favor on-demand billing for simplicity and flexibility over spot instances, reservations, and custom quotes.
- Location: We blend both datacenter proximity and provider HQ location. Datacenter location matters for latency, while HQ location matters for compliance and support.
- 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 | |
|---|---|---|---|---|---|---|---|---|---|
Vast.ai
Our sponsor
|
1x A10 1x A10 23GB (25353518) | 23GB | 96 | 85GB | On-Demand Pay-as-you-go pricing. No term commitments. | $0.32 | $0.32 | Available | View |
Azure
|
1x A10 1x A10 4GB (NVadsA10v5) | 4GB | 6 | 55GB | On-Demand Pay-as-you-go pricing. No term commitments. | $0.45 | $0.45 | Available | View |
Lambda Labs
|
1x A10 1x A10 24GB | 24GB | 30 | 226GB | On-Demand Pay-as-you-go pricing. No term commitments. | $1.29 | $1.29 | Unknown | View |
Fly.io
|
1x A10 1x A10 24GB | 24GB | -- | -- | On-Demand Pay-as-you-go pricing. No term commitments. | $1.50 | $1.50 | Unknown | View |
Oracle Cloud
|
1x A10 1x A10 24GB (VM.GPU.A10.1) | 24GB | -- | -- | On-Demand Pay-as-you-go pricing. No term commitments. | $2.00 | $2.00 | Unknown | View |
|
Azure
|
1x A10 1x A10 8GB (NVadsA10v5) | 8GB | 12 | 110GB | On-Demand Pay-as-you-go pricing. No term commitments. | $0.91 | $0.91 | Available | View |
OVH
|
1x A10 1x A10 24GB (a10-45) | 24GB | 30 | 45GB | On-Demand Pay-as-you-go pricing. No term commitments. | $1.00 | $1.00 | Unknown | View |
Sesterce
|
1x A10 1x A10 24GB | 24GB | 30 | 200GB | On-Demand Pay-as-you-go pricing. No term commitments. | $1.42 | $1.42 | Available | View |
|
Azure
|
1x A10 1x A10 12GB (NVadsA10v5) | 12GB | 18 | 220GB | On-Demand Pay-as-you-go pricing. No term commitments. | $1.60 | $1.60 | Available | View |
|
OVH
|
2x A10 2x A10 24GB (a10-90) | 48GB | 60 | 90GB | On-Demand Pay-as-you-go pricing. No term commitments. | $1.00 | $2.00 | Unknown | View |
|
Oracle Cloud
|
2x A10 2x A10 24GB (VM.GPU.A10.2) | 48GB | -- | -- | On-Demand Pay-as-you-go pricing. No term commitments. | $2.00 | $4.00 | Unknown | View |
Cerebrium
|
1x A10 1x A10 24GB | 24GB | 8 | 32GB | On-Demand Billed per second | $1.10 | $1.10 | Unknown | View |
Runcrate
|
1x A10 PCIe 1x A10 24GB PCIe | 24GB | 30 | 200GB | On-Demand Pay-as-you-go pricing. No term commitments. | $1.42 | $1.42 | Available | View |
|
Vast.ai
|
1x A10 1x A10 23GB (20202186) | 23GB | 96 | 64GB | On-Demand Pay-as-you-go pricing. No term commitments. | $0.32 | $0.32 | Available | View |
|
OVH
|
4x A10 4x A10 24GB (a10-180) | 96GB | 120 | 180GB | On-Demand Pay-as-you-go pricing. No term commitments. | $1.00 | $4.00 | Unknown | View |
|
Azure
|
1x A10 1x A10 24GB (NVadsA10v5) | 24GB | 36 | 440GB | On-Demand Pay-as-you-go pricing. No term commitments. | $3.20 | $3.20 | Available | View |
Alibaba Cloud
|
1x A10 1x A10 24GB (ecs.gn7i-c8g1.2xlarge) | 24GB | 8 | 30GB | On-Demand Pay-as-you-go pricing. No term commitments. | $2.34 | $2.34 | Unknown | View |
|
Oracle Cloud
|
4x A10 4x A10 24GB (BM.GPU.A10.4) | 96GB | -- | -- | On-Demand Pay-as-you-go pricing. No term commitments. | $2.00 | $8.00 | Unknown | View |
|
Alibaba Cloud
|
1x A10 1x A10 24GB (ecs.gn7i-c16g1.4xlarge) | 24GB | 16 | 60GB | On-Demand Pay-as-you-go pricing. No term commitments. | $2.48 | $2.48 | Unknown | View |
|
Azure
|
1x A10 1x A10 24GB (NVadsA10v5) | 24GB | 36 | 880GB | On-Demand Pay-as-you-go pricing. No term commitments. | $4.52 | $4.52 | 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 A10?
24GB GDDR6 with Ampere Tensor Cores. Good balance of price and performance for inference. Wide cloud availability and mature driver support.
When is the A10 not a good fit?
PCIe-only, no NVLink. 24GB VRAM limits model sizes. Lacks FP8 support found in Ada Lovelace GPUs (L4, L40S). For new inference deployments, consider the L4.
Are A10 prices going up or down?
On-demand pricing has increased by about 14% since June 2025, from $1.73 to $1.97/hr per GPU.
What size AI models can the A10 run?
With 24GB of VRAM, the A10 can typically run 7B to 13B models in FP16, or larger models in 4-bit quantized form.
How much VRAM does the A10 have?
The A10 has 24GB of VRAM. Multi-GPU setups increase total memory, but that memory is not automatically pooled across GPUs.
What is the A10's memory bandwidth?
The A10 has 600 GB/s of memory bandwidth. Higher bandwidth helps with faster data transfer between GPU memory and compute cores.
What data types does the A10 support?
The A10 supports 6 precision formats. Training: BF16, FP16, TF32, FP32. Inference: INT4, INT8.
Does the A10 support NVLink?
No. The A10 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 A10 cost per hour?
A10 pricing currently ranges from $0.09/hr to $4.52/hr per GPU, depending on the provider, instance type, and billing model.
How much does the A10 cost per month?
At 720 hours per month, one A10 can cost between $65.38 to $3,254.40 per month, depending on the provider. Reserved and spot pricing can lower that further.
Which cloud providers offer the A10?
The A10 is available from 10 cloud providers, including OVHcloud, Cerebrium, Runcrate. Pricing and availability vary by region and billing model.
Can I rent the A10 in the cloud?
Yes. We currently track 63 A10 listings across 10 cloud providers:
Billing type Listings Avg $/GPU/hr On-demand 32 $1.87/hr Reserved 25 $1.47/hr Spot 6 $0.44/hr
Technical Specifications
| FP32 | 31.2 TF |
| TF32 Tensor Core | 62.5 TF / 125 TF |
| BFLOAT16 Tensor Core | 125 TF / 250 TF |
| FP16 Tensor Core | 125 TF / 250 TF |
| INT8 Tensor Core | 250 TOPS / 500 TOPS |
| INT4 Tensor Core | 500 TOPS / 1000 TOPS |
| RT Cores | 72 |
| Encode / Decode | 1 encoder, 1 decoder (+AV1 decode) |
| GPU Memory | 24 GB GDDR6 |
| GPU Memory Bandwidth | 600 GB/s |
| Interconnect | PCIe Gen4: 64 GB/s |
| Form Factor | 1-slot FHFL |
| Max TDP Power | 150W |
| vGPU Software Support | NVIDIA vPC/vApps, NVIDIA RTX™ vWS, NVIDIA Virtual Compute Server (vCS) |
| Secure and Measured Boot with Hardware Root of Trust | Yes |
| NEBS Ready | Level 3 |
| Power Connector | PEX 8-pin |
Source: official Nvidia A10 datasheet.
Alternatives to Nvidia A10
Last updated