A16
nvidia · ampere · 64 GB GDDR6 · 250W TDP
VRAM
64 GB
BF16 TFLOPS
16.8
Bandwidth
232 GB/s
From
$0.72/hr
Spec Sheet
Pricing by Provider
| Provider | On-Demand | Reserved | Spot | Badge |
|---|---|---|---|---|
| aws | $1.10/hr | $0.72/hr | - | Cheapest |
Compatible Models (277)
Single GPU (204 models)
Multi-GPU (73 models)
Training Capabilities
Estimated GPU count for full fine-tuning (AdamW, BF16) and QLoRA
| Model Size | Full Fine-Tune | QLoRA |
|---|---|---|
| 7B model | 3 GPUs | 1 GPU |
| 13B model | 4 GPUs | 1 GPU |
| 70B model | 21 GPUs | 1 GPU |
Energy Efficiency
Estimated tokens/second per Watt for popular models
Similar GPUs
| GPU | VRAM | BF16 TFLOPS | BW (GB/s) | From |
|---|---|---|---|---|
| A100 80GB SXM | 80 GB | 312 | 2039 | $1.19/hr |
| A100 80GB PCIe | 80 GB | 312 | 2039 | $1.05/hr |
| RTX A6000 | 48 GB | 38.7 | 768 | $0.49/hr |
| A40 | 48 GB | 37.4 | 696 | $0.42/hr |
| A100 40GB SXM | 40 GB | 312 | 1555 | $0.85/hr |
Methodology Note
Performance estimates for the A16are based on InferenceBench's roofline performance model with CUDA kernel-level optimization including FlashAttention v2 and PagedAttention. Memory calculations account for model weights (64 GB GDDR6 available), KV-cache allocation, and activation memory. Throughput predictions use the A16's rated 232 GB/s memory bandwidth and 16.8 BF16 TFLOPS compute capacity as roofline ceilings, with empirical correction factors per GPU architecture (ampere). See our full methodology.
Frequently Asked Questions
How many AI models can run on A16?
The A16 can run 277 AI models from our database within a single node. Compatible models range across various parameter sizes depending on the quantization precision (BF16, FP8, INT4). Smaller models fit on a single GPU while larger models may require multi-GPU setups up to 8x A16.
What is the A16 inference throughput?
The A16 delivers 16.8 BF16 TFLOPS and 16.8 FP8 TFLOPS with 232 GB/s memory bandwidth. Actual inference throughput (tokens/sec) depends on the model size, precision, and batch size. Use our calculator for model-specific throughput estimates.
How much does A16 cost per hour?
The A16 is available starting from $0.72/hour via aws. Prices vary by provider and pricing tier (on-demand, reserved, spot). Compare pricing across all providers in the table above.