A30
See rental prices ↓TDP 165W · 165 TFLOPS · 24GB VRAM · 933 GB/s bandwidth
The A30 has a 165W TDP, 165 TFLOPS of FP16 compute, 24GB of HBM2 VRAM, 933 GB/s memory bandwidth.
Slimmed-down A100 die with HBM2. Excellent memory bandwidth for its TDP class.
A30 has 24GB of memory. Compare its specs and listed cloud rental prices below. The workload must fit in VRAM with room for runtime memory; a listed price does not confirm stock.
A30 Overview
The NVIDIA A30 is a 165W Ampere data-center accelerator derived from the GA100 family, delivering 24GB of HBM2 and 165 TFLOPS of FP16/BF16 throughput. It targets deployments that need data-center features and HBM bandwidth without the power draw or cost of a full A100.
Its 933 GB/s of HBM2 bandwidth is unusually strong for a 24GB, low-power card and is valuable for serving models that fit in memory. The 24GB capacity still limits full-precision model placement and context cache, but NVLink 3.0 and MIG support give operators options for multi-GPU layouts and partitioned, multi-tenant services.
The A30 is a sensible fit for efficient inference at scale, lower-power HPC, and organizations that need predictable Ampere behavior. It is not ideal for very large models, FP8 pipelines, or tasks that require high FP32 performance for graphics-heavy or simulation-oriented work.
Memory
Compute Performance
Hardware Specifications
Chip
Processors
Clocks
Memory
Power
Relative Performance
Relative to highest-spec GPU in database
Limitations
Live Cloud PricingOn-demand hourly rates
Compare A30 vs…
Use Case Guidance
LLM Model Size Guidance
Estimates only. Actual capacity depends on context length, KV cache, and framework overhead.
Related Guides
LLM APIs Running on This GPU Class
Providers that serve frontier LLM inference on Ampere-class hardware.
A30 vs Alternatives — Spec Comparison
| Spec | A30 this | RTX 4090 | L40 | RTX 5880 Ada |
|---|---|---|---|---|
| VRAM | 24GB HBM2 | 24GB GDDR6X | 48GB GDDR6▲ | 48GB GDDR6▲ |
| Memory Bandwidth | 933 GB/s | 1008 GB/s▲ | 864 GB/s | 960 GB/s |
| FP16 TFLOPS | 165 | 165.2 | 181▲ | 181▲ |
| BF16 TFLOPS | 165 | 165.2 | 181▲ | 181▲ |
| FP8 TFLOPS | — | — | — | — |
| INT8 TOPS | 330 | 330.3 | 362▲ | 362▲ |
| TDP | 165W | 450W▲ | 300W | 285W |
| Process Node | TSMC 7nm▲ | TSMC 4N | TSMC 4N | TSMC 4N |
| Architecture | GA100 | AD102▲ | AD102▲ | AD102▲ |
| Release Year | 2021 | 2022 | 2022 | 2024▲ |
| Max model (FP16) | ~12B params | ~12B params | ~24B params▲ | ~24B params▲ |
| Max model (INT4) | ~48B params | ~48B params | ~96B params▲ | ~96B params▲ |
Related GPUs
A30 Frequently Asked Questions
What is the A30 TDP?
The A30 has a TDP (Thermal Design Power) of 165W.
How many TFLOPS does the A30 have?
The A30 delivers 165 TFLOPS of FP16 compute and 165 TFLOPS BF16.
How much VRAM does the A30 have?
The A30 has 24GB of HBM2 VRAM.
What is the A30's memory bandwidth?
The A30 has a memory bandwidth of 933 GB/s.
A30 User Reviews
A30 User Reviews
Ready to rent?
Compare A30 prices across 130+ providers
Live on-demand & spot rates · monthly cost estimates · availability status