Inference in a server environment
Measure service latency and throughput with a realistic request queue.
L40S rental
A data center GPU with RT cores for inference, rendering and video workloads.
$0.872/ hour
Consider ASUS GX10 for LLMs
Choosing L40S to run a language model? Compare your workload with ASUS Ascent GX10 rental: NVIDIA GB10 and 128 GB of unified CPU and GPU memory on one node.
Request one ASUS system for inference and RAG, or a pair for parallel workloads. Compare model and context memory, ARM64 support and the time needed for a trial run. GX10 unified memory and dedicated VRAM have different trade-offs.
Match ASUS GX10 to your modelASUS Ascent GX10
128 GB unified memory · NVIDIA GB10 · one system or a pair. Availability and software are agreed for your workload.
Offer ends in—d—h—m—s
Workloads for this GPU configuration
Rendering and visualization
L40S combines compute capabilities with RT cores for graphics workloads.
Video processing
Test decoding, AI processing and encoding together as one pipeline.
Software compatibility
- The GPU has 48 GB of GDDR6. Include runtime memory and working buffers in the total.
- Budget the shared 48 GB GPU capacity across your model and video pipeline, including intermediate frames.
- L40S does not support NVLink. Multi-card setups need an explicit data transfer plan.
Rent L40S
Provide your model, software environment and rental period. We will confirm the rate, availability and connection method before the rental starts.
$0.872/ hour
About this configuration
How much memory does L40S have?
The GPU has 48 GB of GDDR6. Include runtime memory and working buffers in the total.
Can L40S handle both AI and graphics?
L40S includes Tensor and RT cores as well as video processing engines. To run several stages together, check application support and their combined memory use.
How do I request this configuration?
This configuration is open for rental requests. Share your workload, preferred dates and duration. Hardware availability, pricing and access dates are confirmed individually; a request does not create a confirmed booking.
