Two independent experiments
Run separate jobs on each card when each fits within its own 24 GB.
2 × RTX 4090 rental
Two cards with 24 GB each for separate workloads or supported multi-GPU runs.
$1.424/ hour
Consider ASUS GX10 for LLMs
Choosing 2 × RTX 4090 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.
RTX 4090 or ASUS GX10 for LLMsASUS 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
Parallel frame rendering
Distribute frames through an engine or queue that supports multiple GPUs.
Multi-GPU experiments
Test model distribution in your runtime and measure communication overhead.
Software compatibility
- Memory is per card: 2 × 24 GB GDDR6X. It is not automatically pooled.
- Each RTX 4090 has its own 24 GB. Your application must support multiple GPUs.
- For one distributed model, confirm PCIe topology and measure cross-GPU communication.
Rent 2 × RTX 4090
Provide your model, software environment and rental period. We will confirm the rate, availability and connection method before the rental starts.
$1.424/ hour
About this configuration
Is memory pooled across all GPUs?
Memory is per card: 2 × 24 GB GDDR6X. It is not automatically pooled.
Will two GPUs be twice as fast?
Independent jobs can run on both cards in parallel. For one job, results depend on work distribution and data transfers; linear scaling is not guaranteed.
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.
