NVIDIA Tesla T4 full datasheet — the specs that matter for deep learning
💡 Answer
NVIDIA Tesla T4 is a 2018-generation Turing card with 16 GB of GDDR6 memory and 320 GB/s bandwidth. Compute peaks at 65 FP16 TFLOPS and 8.1 FP32 TFLOPS; TDP sits at 70W.
The VRAM/bandwidth pairing is the defining feature for machine learning work — it determines what model sizes are accessible and how hard the card can be pushed during production inference. Power draw and cooling requirements mean most NVIDIA Tesla T4 deployments live in data centres rather than workstations, which is why most NVIDIA Tesla T4 access in practice comes via the cloud.
Rent NVIDIA Tesla T4 on Vast.ai from $0.08/hr — check live availability and deploy.
More FAQs about NVIDIA Tesla T4
Vast.ai GPU Provider Review & Key Facts (April 2026)
Snapshot of Vast.ai: GPU models, pricing, billing granularity, infrastructure, developer tools, support channels, and compliance. Data verified April 2026.
|
Vast.ai
Instant GPUs. Transparent Pricing.
|
|
|---|---|
| Overview | |
| Trustpilot Rating | 4.4 |
| Headquarters | United States |
| Provider Type | GPU Marketplace |
| Best For | AI training inference fine-tuning Stable Diffusion batch processing research LLM serving generative AI |
| GPU Hardware | |
| GPU Models | B200 H200 H100 SXM H100 NVL A100 SXM A100 PCIe RTX 5090 RTX 5080 RTX 5070 Ti RTX 6000 Pro RTX 6000 Ada RTX 4500 Ada RTX A6000 RTX A5000 RTX A4000 L40S L40 A40 A10 RTX 4090 RTX 4080 RTX 4070 Ti RTX 4070 RTX 4060 Ti RTX 4060 RTX 3090 Ti RTX 3090 RTX 3080 Ti RTX 3080 RTX 3070 Ti RTX 3070 Tesla V100 Tesla T4 A2 GTX 1080 |
| Max VRAM (GB) | 192 |
| Max GPUs/Instance | 8 |
| Interconnect | NVLink, InfiniBand |
| Pricing | |
| Starting Price ($/hr) | $0.06/hr |
| Billing Granularity | Per-second |
| Spot/Preemptible | Yes |
| Reserved Discounts | Up to 50% (1-6 month reserved) |
| Free Credits | Small test credit on signup |
| Egress Fees | Varies by host ($/TB) |
| Storage | Varies by host ($/GB/hr, charged while instance exists) |
| Infrastructure | |
| Regions | 500+ locations, 40+ data centers |
| Uptime SLA | No formal SLA (host reliability scores visible) |
| Developer Experience | |
| Frameworks | PyTorch TensorFlow CUDA vLLM ComfyUI |
| Docker Support | Yes |
| SSH Access | Yes |
| Jupyter Notebooks | Yes |
| API / CLI | Yes |
| Setup Time | Seconds |
| Kubernetes Support | No |
| Business Terms | |
| Min Commitment | None |
| Compliance | SOC 2 Type 2 HIPAA GDPR CCPA |
Vast.ai