NVIDIA / Ampere
A10
| Provider / plan | Price / GPU-hour | Rental type | Terms & configuration | Last checked | Provider pricing link |
|---|---|---|---|---|---|
| Vast.aiOn-demand offer 52500309 | $0.2348Lowest flexible rate | On-demandNo reservation | 1 GPU minimumCalifornia, USView detailsObserved marketplace offer, not a provider-wide list rate. Total hourly quote for one GPU with the API default disk allocation; bandwidth and additional storage can cost extra. Up to 5 cheapest matching offers per catalog GPU; availability can change.
|
2026-10-03Auto-collected | View pricing ↗ |
| ModalGPU Tasks | $1.1016GPU only · CPU/RAM extra | ServerlessActive GPU time | 1 GPU minimumSee providerView detailsGPU time only; CPU, RAM, storage, region and non-preemptible surcharges are extra.
|
2026-10-03Auto-collected | View pricing ↗ |
Prices are dated listings, not live availability. Compare minimum GPU counts and commitments. Storage, networking and taxes may add charges; serverless rates cover GPU time only.
A10 is a 24 GB Ampere server GPU for inference, graphics and video workloads. Its single-slot 150 W design fits mainstream enterprise servers. It is a useful comparison point for moderate-memory inference and virtual workstation use.
CHOOSING THIS GPU
Is it right for your workload?
NVIDIA A10 reference GPU. Provider-specific derivatives and virtual slices may expose different usable memory or performance.
Best suited to
- Moderate-memory model inference
- Virtual workstations and rendering
- Video analytics and AI-assisted graphics
Strengths
- 24 GB GDDR6
- 600 GB/s memory bandwidth
- Single-slot 150 W design
Things to consider
- No native FP8 Tensor acceleration
- 24 GB model-memory budget
- Virtualization configuration and licensing vary by provider
HARDWARE DETAILS
Inside the GPU
- Manufacturer
- NVIDIA
- Architecture
- Ampere
- VRAM (GB)
- 24
- Memory type
- GDDR6
- Form factor
- PCIe
- Memory bandwidth (GB/s)
- 600
- Maximum board power (W)
- 150
- CUDA cores
- Not verified for this edition
- Tensor cores
- 3rd generation
- Ray tracing cores
- 72 / 2nd generation
- CUDA capability
- 8.6
- Memory ECC
- Supported; enabled by default
- Host interface
- PCIe Gen4
- GPU interconnect
- Not verified for this edition
- Hardware partitioning (MIG)
- Not verified for this edition
- Cooling
- Passive; server airflow required
Hardware capabilities are not a guarantee of access in a cloud instance. Check the exact edition, GPU allocation and server topology in the rental offer.
MODEL MEMORY
Plan your model size
Start with an 8B-class model in a supported 4-bit format. FP16 8B weights alone are about 16 GB before runtime memory; reserve room for KV cache and activations. Adapter fine-tuning needs a separate training memory estimate.
| Example model class | Weight format | Raw weights ≈ | Minimum GPUs for weights only |
|---|---|---|---|
| Llama 3.1 8B ↗ | 4-bit | 4 GB | 1Runtime needs more memory |
| Llama 3.1 8B ↗ | FP16 | 16 GB | 1Runtime needs more memory |
| Qwen2.5 14B ↗ | 4-bit | 7 GB | 1Runtime needs more memory |
| Qwen2.5 32B ↗ | 4-bit | 16 GB | 1Runtime needs more memory |
| Llama 3.1 70B ↗ | 4-bit | 35 GB | 2Runtime needs more memory |
| Llama 3.1 70B ↗ | 8-bit | 70 GB | 3Runtime needs more memory |
| Llama 3.1 70B ↗ | FP16 | 140 GB | 6Runtime needs more memory |
Arithmetic lower bound: rounded parameter count × bits per weight ÷ 8, in decimal GB. Excludes quantization metadata, KV cache, activations, CUDA workspaces and training states. Actual model sizes differ from their rounded names. No context length, batch size or concurrency is guaranteed. GPU counts assume supported model sharding and can be higher in practice. Quantized checkpoints and compatible kernels are required for 4-bit/8-bit execution.
SOFTWARE & PERFORMANCE
Before you deploy
Software compatibility
Use an NVIDIA CUDA-enabled framework/container compatible with this GPU and the host driver. Check PyTorch build and inference-engine kernel requirements before deployment. vLLM documents NVIDIA compute capability 7.5+ as a baseline; support for each model and quantization method still needs checking.
Measured benchmarks
A reproducible, comparable application benchmark has not yet been recorded for this edition. Peak TFLOPS above are not measured tokens per second or image-generation speed.
Compare tests using the same model, precision, GPU count, engine version, input/output length and batch or concurrency. A provider’s server configuration can change the result.
COMPARE YOUR OPTIONS
Alternatives to consider
BUDGET YOUR RUN
GPU cost estimator
GPU compute only: hourly rate × billable hours × GPU count. CPU, RAM, storage, egress, taxes, billing increments and minimum terms may add charges. Serverless hours mean active GPU task time; spot capacity can be interrupted. Reserved commitments and quote-only offers are excluded from this simple hourly estimator.