Nvidia A10G
AWS-optimized GPU for inference, rendering, and video transcoding.
Compare vs other GPUs →Key Specifications
Compare Cloud Provider Prices
For smaller projects, the A10G is available around $0.39/hr per GPU (spot instance). This tier offers a 90% discount compared to the higher end of the market ($4.10/hr).
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
|
2x A10G 2x A10G 23GB (38002278) | 46GB | 48 | 95GB | Spot Variable spot pricing with potential interruptions. | $0.39 | $0.77 | Available | View |
AWS
|
1x A10G 1x A10G 24GB (g5.xlarge) | 24GB | 4 | 16GB | On-Demand Pay-as-you-go pricing. No term commitments. | $1.01 | $1.01 | Available | View |
|
AWS
|
1x A10G 1x A10G 24GB (g5.2xlarge) | 24GB | 8 | 32GB | On-Demand Pay-as-you-go pricing. No term commitments. | $1.21 | $1.21 | Available | View |
|
AWS
|
1x A10G 1x A10G 24GB (g5.4xlarge) | 24GB | 16 | 64GB | On-Demand Pay-as-you-go pricing. No term commitments. | $1.62 | $1.62 | Available | View |
|
AWS
|
1x A10G 1x A10G 24GB (g5.8xlarge) | 24GB | 32 | 128GB | On-Demand Pay-as-you-go pricing. No term commitments. | $2.45 | $2.45 | Available | View |
|
Vast.ai
|
2x A10G 2x A10G 23GB (38002280) | 46GB | 48 | 95GB | On-Demand Pay-as-you-go pricing. No term commitments. | $0.73 | $1.47 | Available | View |
Beam
|
1x A10G 1x A10G 24GB | 24GB | 4 | 8GB | On-Demand Billed per millisecond. Total: $1.05 GPU + $0.19×4 CPU + $0.02×8 RAM per hour | $1.97 | $1.97 | Unknown | View |
|
AWS
|
4x A10G 4x A10G 24GB (g5.12xlarge) | 96GB | 48 | 192GB | On-Demand Pay-as-you-go pricing. No term commitments. | $1.42 | $5.67 | Available | View |
|
Vast.ai
|
4x A10G 4x A10G 23GB (38002279) | 92GB | 48 | 191GB | On-Demand Pay-as-you-go pricing. No term commitments. | $0.73 | $2.93 | Available | View |
|
AWS
|
1x A10G 1x A10G 24GB (g5.16xlarge) | 24GB | 64 | 256GB | On-Demand Pay-as-you-go pricing. No term commitments. | $4.10 | $4.10 | Available | View |
|
AWS
|
1x A10G 1x A10G 24GB (g5.xlarge) | 24GB | 4 | 16GB | Reserved (36mo) Reserved capacity with a 3-year minimum commitment. | $0.43 | $0.43 | Available | View |
|
AWS
|
1x A10G 1x A10G 24GB (g5.2xlarge) | 24GB | 8 | 32GB | Reserved (36mo) Reserved capacity with a 3-year minimum commitment. | $0.65 | $0.65 | Available | View |
|
AWS
|
1x A10G 1x A10G 24GB (g5.4xlarge) | 24GB | 16 | 64GB | Reserved (36mo) Reserved capacity with a 3-year minimum commitment. | $0.70 | $0.70 | Available | View |
|
Vast.ai
|
4x A10G 4x A10G 23GB (38002279) | 92GB | 48 | 191GB | Spot Variable spot pricing with potential interruptions. | $0.39 | $1.55 | Available | View |
|
AWS
|
1x A10G 1x A10G 24GB (g5.2xlarge) | 24GB | 8 | 32GB | Reserved (12mo) Reserved capacity with a 1-year minimum commitment. | $0.76 | $0.76 | Available | View |
|
AWS
|
1x A10G 1x A10G 24GB (g5.xlarge) | 24GB | 4 | 16GB | Reserved (12mo) Reserved capacity with a 1-year minimum commitment. | $0.79 | $0.79 | Available | View |
|
AWS
|
4x A10G 4x A10G 24GB (g5.24xlarge) | 96GB | 96 | 384GB | On-Demand Pay-as-you-go pricing. No term commitments. | $2.04 | $8.14 | Available | View |
|
AWS
|
1x A10G 1x A10G 24GB (g5.4xlarge) | 24GB | 16 | 64GB | Reserved (12mo) Reserved capacity with a 1-year minimum commitment. | $1.02 | $1.02 | Available | View |
|
AWS
|
1x A10G 1x A10G 24GB (g5.8xlarge) | 24GB | 32 | 128GB | Reserved (36mo) Reserved capacity with a 3-year minimum commitment. | $1.32 | $1.32 | Available | View |
|
AWS
|
1x A10G 1x A10G 24GB (g5.8xlarge) | 24GB | 32 | 128GB | Reserved (12mo) Reserved capacity with a 1-year minimum commitment. | $1.54 | $1.54 | 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 A10G?
24GB GDDR6, AWS-optimized variant of the A10. Good for inference, graphics rendering, and video transcoding on AWS. Widely available on G5 instances.
When is the A10G not a good fit?
AWS-only availability. No NVLink, no FP8. For multi-cloud or non-AWS deployments, the standard A10 or L4 is a better fit.
Are A10G prices going up or down?
On-demand pricing has decreased by about 4% since June 2025, dropping from $1.85 to $1.77/hr per GPU.
What size AI models can the A10G run?
With 24GB of VRAM, the A10G can typically run 7B to 13B models in FP16, or larger models in 4-bit quantized form.
How much VRAM does the A10G have?
The A10G has 24GB of VRAM. Multi-GPU setups increase total memory, but that memory is not automatically pooled across GPUs.
What is the A10G's memory bandwidth?
The A10G 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 A10G support?
The A10G supports 6 precision formats. Training: BF16, FP16, TF32, FP32. Inference: INT4, INT8.
Does the A10G support NVLink?
No. The A10G 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 A10G cost per hour?
A10G pricing currently ranges from $0.39/hr to $4.10/hr per GPU, depending on the provider, instance type, and billing model.
How much does the A10G cost per month?
At 720 hours per month, one A10G can cost between $278.64 to $2,949.12 per month, depending on the provider. Reserved and spot pricing can lower that further.
Which cloud providers offer the A10G?
The A10G is available from 3 cloud providers: Amazon Web Services, Beam, Vast.ai.
Can I rent the A10G in the cloud?
Yes. We currently track 29 A10G listings across 3 cloud providers:
Billing type Listings Avg $/GPU/hr On-demand 11 $1.76/hr Reserved 16 $1.22/hr Spot 2 $0.39/hr
Technical Specifications
| FP32 | 35 TF |
| TF32 Tensor Core | 35 TF |
| BFLOAT16 Tensor Core | 70 TF |
| FP16 Tensor Core | 70 TF |
| INT8 Tensor Core | 140 TOPS |
| INT4 Tensor Core | 280 TOPS |
| RT Cores | 80 |
| Encode / Decode | 1 encoder, 2 decoder (+AV1 decode) |
| GPU Memory | 24 GB GDDR6 |
| GPU Memory Bandwidth | 600 GB/s |
| Interconnect | PCIe Gen4: 64 GB/s |
| Form Factor | 2-slot FHFL |
| Max TDP Power | 300W |
| vGPU Software Support | NVIDIA RTX™ vWS |
Source: official Nvidia A10G datasheet.
Alternatives to Nvidia A10G
Last updated