NVIDIA
A30
Provider Marketplace
All Cloud Providers
Estimates only — rates are collected automatically from public provider pages and may be out of date.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 .
Compute Performance
Architecture
Memory & VRAM
Connectivity & Scaling
Virtualization
Power & Efficiency
Physical Design
Software Ecosystem
Server & Deployment
System Compatibility
Benchmarks & Throughput
Structured Sparsity
Supported (up to 2X more performance)
Training Benchmarks
AI Training—Up to 3X higher throughput than v100 and 6X higher than T4
Inference Benchmarks
AI Inference—Up To 3X higher throughput than V100 at real-time conversational AI
Scaling Efficiency
Can scale to thousands of GPUs when combined with NVLink, PCIe Gen4, networking and Magnum IO
Multi-GPU Scalability
Scaling Characteristics
Workload Readiness
LLM Training
AI Training—Up to 3X higher throughput than v100 and 6X higher than T4
LLM Inference
AI Inference—Up To 3X higher throughput than V100 at real-time conversational AI
HPC / Simulation
HPC—Up to 1.1X higher throughput than V100 and 8X higher than T4
Scientific Computing
FP64 5.2 teraFLOPS
Real-Time Serving
BERT Large Inference (Normalized) Throughput for <10ms Latency
Market Authority
MLPerf Ranking
NVIDIA set multiple performance records in MLPerf
Community Benchmarks
MLPerf benchmark data referenced
Key Strengths
Limitations
Also in the Lineup
Expert Insight
The A30 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.