Hopper80 GB
NVIDIA H100
AI training, inference and accelerated computing
- Memory
- HBM3
- Status
- On request
Price on requestConfiguration and region to be confirmed
Explore model GPU CLOUD
GPU cloud servers
From your first AI experiment to memory-intensive training. Choose a GPU around your workload, then configure its server and location.
Explore GPUsHARDWARE CATALOG
Find your GPU
Model specifications are separate from rental availability. Use the availability filter to see confirmed offers only.
Models found: 27
Ada Lovelace24 GB
NVIDIA RTX 4090
Prototyping, image generation and rendering
- Memory
- GDDR6X
- Status
- On request
Price on requestConfiguration and region to be confirmed
Explore model Ampere80 GB
NVIDIA A100
Established CUDA workloads and model training
- Memory
- HBM2e
- Status
- On request
Price on requestConfiguration and region to be confirmed
Explore model Blackwell Ultra288 GB
NVIDIA B300
Large model inference and multi-GPU training
- Memory
- HBM3e
- Status
- On request
Price on requestConfiguration and region to be confirmed
Explore model Blackwell180 GB
NVIDIA B200
Training and inference with high memory demand
- Memory
- HBM3e
- Status
- On request
Price on requestConfiguration and region to be confirmed
Explore model Hopper141 GB
NVIDIA H200
Memory-intensive LLM inference and scientific computing
- Memory
- HBM3e
- Status
- On request
Price on requestConfiguration and region to be confirmed
Explore model Ampere48 GB
NVIDIA A40
Rendering, virtual workstations and inference
- Memory
- GDDR6 ECC
- Status
- On request
Price on requestConfiguration and region to be confirmed
Explore model Ampere24 GB
NVIDIA A10
Graphics, inference and compact AI services
- Memory
- GDDR6 ECC
- Status
- On request
Price on requestConfiguration and region to be confirmed
Explore model Ada Lovelace48 GB
NVIDIA L40S
Generative AI, rendering and video workloads
- Memory
- GDDR6 ECC
- Status
- On request
Price on requestConfiguration and region to be confirmed
Explore model Ada Lovelace48 GB
NVIDIA L40
Professional graphics, rendering and simulation
- Memory
- GDDR6 ECC
- Status
- On request
Price on requestConfiguration and region to be confirmed
Explore model Ada Lovelace24 GB
NVIDIA L4
Video processing, inference and graphics services
- Memory
- GDDR6
- Status
- On request
Price on requestConfiguration and region to be confirmed
Explore model Blackwell32 GB
NVIDIA RTX 5090
Development, rendering and single-GPU experiments
- Memory
- GDDR7
- Status
- On request
Price on requestConfiguration and region to be confirmed
Explore model CDNA 3192 GB
AMD Instinct MI300X
LLM inference and ROCm training
- Memory
- HBM3
- Status
- On request
Price on requestConfiguration and region to be confirmed
Explore model CDNA 3256 GB
AMD Instinct MI325X
Large working sets and multi-accelerator AI
- Memory
- HBM3e
- Status
- On request
Price on requestConfiguration and region to be confirmed
Explore model Hopper80 GB
NVIDIA H100 PCIe
PCIe-based CUDA training and inference
- Memory
- HBM2e
- Status
- On request
Price on requestConfiguration and region to be confirmed
Explore model Hopper94 GB
NVIDIA H100 NVL
Memory-intensive inference with NVLink requirements
- Memory
- HBM3
- Status
- On request
Price on requestConfiguration and region to be confirmed
Explore model Blackwell192 GB
NVIDIA B100
Blackwell training and inference platforms
- Memory
- HBM3e
- Status
- On request
Price on requestConfiguration and region to be confirmed
Explore model Ada Lovelace48 GB
NVIDIA RTX 6000 Ada
Professional rendering, visualization and AI
- Memory
- GDDR6 ECC
- Status
- On request
Price on requestConfiguration and region to be confirmed
Explore model Blackwell96 GB
NVIDIA RTX PRO 6000 Blackwell
Server graphics, inference and rendering
- Memory
- GDDR7 ECC
- Status
- On request
Price on requestConfiguration and region to be confirmed
Explore model Ampere48 GB
NVIDIA RTX A6000
Ampere visualization, rendering and model development
- Memory
- GDDR6 ECC
- Status
- On request
Price on requestConfiguration and region to be confirmed
Explore model Volta32 GB
NVIDIA V100 32 GB
Existing CUDA applications and scientific computing
- Memory
- HBM2
- Status
- On request
Price on requestConfiguration and region to be confirmed
Explore model Volta16 GB
NVIDIA V100 16 GB
Existing CUDA applications and scientific computing
- Memory
- HBM2
- Status
- On request
Price on requestConfiguration and region to be confirmed
Explore model Turing16 GB
NVIDIA T4
Compact inference and video processing
- Memory
- GDDR6
- Status
- On request
Price on requestConfiguration and region to be confirmed
Explore model Ampere24 GB
NVIDIA RTX 3090
Image generation, prototyping and GPU rendering
- Memory
- GDDR6X
- Status
- On request
Price on requestConfiguration and region to be confirmed
Explore model Grace Hopper144 GB
NVIDIA GH200 144 GB
Arm-based AI and coherent CPU/GPU workloads
- Memory
- HBM3e
- Status
- On request
Price on requestConfiguration and region to be confirmed
Explore model Grace Hopper96 GB
NVIDIA GH200 96 GB
Arm-based AI and coherent CPU/GPU workloads
- Memory
- HBM3
- Status
- On request
Price on requestConfiguration and region to be confirmed
Explore model Grace Blackwell186 GB / GPU
NVIDIA GB200 NVL72
Rack-scale AI training and large-model serving
- Memory
- HBM3e
- Status
- On request
Price on requestConfiguration and region to be confirmed
Explore model LOCATION
Choose a region for your workload
Keep compute close to your data and users. Capacity is checked for the selected model and location.
Europe
Availability on request
USA
Availability on request
Asia
Availability on request
Start with your workload
Describe your GPU, memory and region requirements in Atlas Ai Navigator.