Ampere
NVIDIA RTX 3090
wins
1
The RTX 3090 remains a popular budget option for AI workloads with 24GB GDDR6X.
Ampere
NVIDIA A10
wins
3
The NVIDIA A10 is a versatile Ampere GPU with 24GB GDDR6 and 150W TDP.
Performance comparison
Visual bars — winner highlighted
NVIDIA RTX 3090
Metric
NVIDIA A10
FP16 TFLOPS
Bandwidth
VRAM
TDP (lower=better)
TFLOPS/watt
GB/s per watt
Full specification table
| Spec | NVIDIA RTX 3090 | NVIDIA A10 |
|---|---|---|
| Architecture | Ampere | Ampere |
| VRAM | 24 GB GDDR6X | 24 GB GDDR6 |
| VRAM type | GDDR6X | GDDR6 |
| Memory bandwidth | 936 GB/s | 600 GB/s |
| FP16 TFLOPS | 71 TFLOPS | 125 TFLOPS |
| TDP | 350 W | 150 W |
| TFLOPS/watt | 0.20 T/W | 0.83 T/W |
| GB/s per watt | 2.67 GB/s/W | 4.00 GB/s/W |
| NVLink | No | No |
| Release year | 2020 | 2021 |
Live cloud pricing
On-demand $/hr across providers — updated in real time
Power efficiency analysis
TFLOPS/watt and GB/s/watt — critical for data center TCO
NVIDIA RTX 3090
NVIDIA A10
TFLOPS/watt measures compute efficiency — how much AI throughput you get per watt of power consumed. For data centers with PUE of 1.2–1.5, a 10% improvement in TFLOPS/watt translates directly to lower electricity costs and cooling requirements. GB/s/watt measures memory bandwidth efficiency, which is the binding constraint for memory-bound LLM inference workloads.
When to choose each GPU
Choose NVIDIA RTX 3090 for:
- Budget fine-tuning
- Small model inference
- Hobbyist AI
Choose NVIDIA A10 for:
- Inference
- Graphics rendering
- Virtual workstations
Popular GPU comparisons