📢 ANNOUCEMENT 1Legion to Deploy $50M in GPUs with Classover
The NVIDIA RTX 5090 is a Blackwell architecture GPU with 21,760 CUDA cores, 32 GB GDDR7 memory, and native FP4 precision support. On 1Legion bare metal, you get full access to the hardware, no virtualisation layer, no shared tenants, no performance variability. Designed for generative AI inference, ComfyUI pipelines, 3D rendering, and compute workloads that need consistent throughput at a predictable hourly rate.
21,760 CUDA cores and 32 GB GDDR7 at full capacity, no shared resources, no throttling.
Native Blackwell precision formats for AI inference and generative workloads.
Consistent throughput, no egress fees, and no variable performance pricing.
Run ComfyUI, Stable Diffusion, image generation, and LLM inference pipelines with full VRAM and memory bandwidth.
Accelerate Blender, Unreal Engine, and real-time rendering workflows with Blackwell architecture and RT Core performance.
Process large datasets and run GPU-accelerated simulations with consistent bare metal performance.
No. All 1Legion GPU instances are available as full bare metal servers only. Minimum rental is the complete 8-GPU machine, ensuring dedicated resources, full memory bandwidth, and no shared infrastructure.
Minimum commitment is 1 month. 12-month and 24-month terms are available at lower per-GPU-hour rates.
Pricing is per GPU per hour, billed for the full 8-GPU server. There are no egress fees, no hidden storage charges, and no variable performance pricing.
Each 1Legion GPU instance page includes a detailed spec comparison against reference hardware. Pricing, VRAM, compute throughput, and workload fit vary by model, see the comparison table on each page for specifics.
Tell us about your workload. Our team will match you with the right server configuration and reach out shortly.
