What GPU models does Vast.ai offer?

💡 Answer

Vast.ai offers a range of GPU models for AI, machine learning, and high-performance computing workloads. The full list of available GPUs includes:

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

The maximum VRAM available on a single GPU at Vast.ai is 192 GB, and instances can be configured with up to 8 GPUs. The interconnect technology used for multi-GPU setups is NVLink, InfiniBand, which determines the bandwidth between GPUs during distributed training.

Browse the full catalog of available GPUs and their specifications at Vast.ai official website.

More FAQs about Vast.ai

Guides Where Vast.ai Is Featured

These guides include Vast.ai alongside other cloud GPU providers, grouped by hardware, pricing, features, and infrastructure.

Vast.ai vs Vultr - GPU Provider Comparison (March 2026)

Head-to-head comparison of Vast.ai and Vultr. Check max funding, profit splits, daily and overall drawdown rules, leverage, tradable assets, payout frequency, payment and payout methods, trading permissions and KYC restrictions before you buy a challenge. Data refreshed March 2026.

Vast.ai vs Vultr - GPU Provider Comparison (March 2026)
Vast.ai
Instant GPUs. Transparent Pricing.
Vultr
High-performance cloud GPU across 32 global regions
Overview
Trustpilot Rating 4.4 1.8
Headquarters United States United States
Provider Type GPU Marketplace Multi-Cloud
Best For AI training inference fine-tuning Stable Diffusion batch processing research LLM serving generative AI AI training inference video rendering HPC Stable Diffusion game development generative AI fine-tuning research
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 A16 A40 L40S A100 PCIe GH200 A100 SXM H100 SXM B200 B300 MI300X MI325X MI355X
Max VRAM (GB) 192 288
Max GPUs/Instance 8 16
Interconnect NVLink, InfiniBand NVLink
Pricing
Starting Price ($/hr) $0.06/hr $0.47/hr
Billing Granularity Per-second Per-hour
Spot/Preemptible 1 1
Reserved Discounts Up to 50% (1-6 month reserved) N/A
Free Credits Small test credit on signup Up to $300 free credit for 30 days
Egress Fees Varies by host ($/TB) Standard (varies by plan)
Storage Varies by host ($/GB/hr, charged while instance exists) 350 GB - 61 TB NVMe (included), Block Storage at $0.10/GB/mo, S3-compatible Object Storage
Infrastructure
Regions 500+ locations, 40+ data centers 32 regions across 6 continents (Americas, Europe, Asia, Australia, Africa)
Uptime SLA No formal SLA (host reliability scores visible) 100%
Developer Experience
Frameworks PyTorch TensorFlow CUDA vLLM ComfyUI PyTorch TensorFlow CUDA cuDNN ROCm Hugging Face NVIDIA NGC
Docker Support 1 1
SSH Access 1 1
Jupyter Notebooks 1 1
API / CLI 1 1
Setup Time Seconds Minutes
Kubernetes Support 0 1
Business Terms
Min Commitment None None
Compliance SOC 2 Type 2 HIPAA GDPR CCPA SOC 2+ (HIPAA) PCI ISO 27001 ISO 27017 ISO 27018 ISO 20000-1 CSA STAR Level 1