NVIDIA

A10G

A10G — illustration of the card's form factor
Architecture
Ampere

Provider Marketplace

Cheapest
$1.21/hour
Starting from
Best Value
Awaiting listings
No additional provider yet
Enterprise Choice
Awaiting listings
No additional provider yet

All Cloud Providers

1 Options available
Baseten logo
BasetenCheapest
On-Demand
$1.21/ hour
Estimated Cost
Provision

Estimates onlyrates are collected automatically from public provider pages and may be out of date. Prices vary by region, commitment term, and availability, and typically exclude storage, egress, and tax. Confirm current pricing with the provider before purchasing. Last collected .

Architecture

MicroarchitectureAmpere

Virtualization

K8s ReadinessSupported via AWS managed services (Amazon EKS/ECS)
Virt EfficiencyNear bare-metal (vendor claim)

Software Ecosystem

Triton Serveravailable on G5 instances

Server & Deployment

OEM AvailabilityGeneral availability on AWS

Multi-GPU Scalability

Scaling Characteristics

ParallelismSupports multiple GPUs (up to eight A10G GPUs per instance); applications like DaVinci Resolve can use multiple GPUs to accelerate effects.

Workload Readiness

Real-Time Serving

G5 instances also deliver the best user experience for real-time AI inference performance at scale for use-cases like content and product recommendations, voice assistants, chatbots, and visual search.

Market Authority

Cloud Adoption

General availability on AWS EC2 G5 instances

Community Benchmarks

SPECviewperf 2020; Blender Cycles; DaVinci Resolve (video editing benchmarks); gaming benchmarks (DLSS / Metro Exodus mentioned)

Key Strengths

Limitations

Expert Insight

The A10G represents a strategic leap in AI compute. When comparing cloud providers, consider not just the hourly rate, but also the interconnect bandwidth (InfiniBand/NVLink) and regional availability which can significantly impact total cost of ownership for large-scale training.

Glossary Terms

FP32 TFLOPS
VRAM
TDP
Cores
Information updated daily. Cloud pricing subject to vendor availability.