NVIDIA RTX PRO 6000 MIG 48GB cloud GPU rental

The NVIDIA RTX PRO 6000 MIG 48GB is a datacenter Blackwell GPU with 48 GB of GDDR7 (MIG slice). On FastInfra it is a good fit for 30B–70B inference, full fine-tuning of mid-size models, video generation. As a rule of thumb, one PRO 6000 MIG 48GB holds the weights of a model of about 19B parameters at 16-bit precision, or about 76B with 4-bit quantization, after leaving room for the KV cache.

The PRO 6000 MIG 48GB runs on the Secure tier in vetted datacenters at $1.39 per GPU-hour.

This is a Multi-Instance GPU (MIG) slice: a hardware-isolated partition of a larger card with its own 48 GB of memory and compute. It costs less than the full GPU and suits inference services, notebooks and CI jobs that do not need the whole card.

Best for

30B–70B inference, full fine-tuning of mid-size models, video generation.

About the Blackwell architecture

RTX Blackwell cards pair fifth-generation Tensor Cores (with FP4 and FP8 support) with GDDR7 memory. They give much of the inference throughput of datacenter parts at a lower hourly price, and suit LLM serving with quantized weights, image and video generation, and fine-tuning of small and mid-size models. Use a CUDA 12.8+ image for full Blackwell support.

Only need inference?

If you want to call an open model such as Llama, Qwen, DeepSeek or GPT-OSS rather than manage a server, the pay-per-token inference API is often cheaper than keeping a GPU busy around the clock. It is OpenAI-compatible and uses the same account and wallet as your pods. Browse every model with live prices.

How much does it cost to rent an NVIDIA RTX PRO 6000 MIG 48GB per hour?

$1.39 per GPU-hour on demand. Billing is per minute while the pod exists, so 24/7 use for a 730-hour month costs about $1,018 per GPU at the lowest on-demand rate. Prices sync from live capacity and are shown before you deploy.

How much VRAM does the NVIDIA RTX PRO 6000 MIG 48GB have?

48 GB of GDDR7 (MIG slice). A pod with 16 GPUs gives 768 GB of combined VRAM for tensor- or pipeline-parallel workloads.

What size LLM can I run on an NVIDIA RTX PRO 6000 MIG 48GB?

Roughly 19B parameters at FP16 or BF16, 38B at 8-bit and 76B at 4-bit on a single GPU, reserving about 20% of VRAM for the KV cache and activations. Mixture-of-experts models need memory for all experts, not only the active ones. Long contexts and large batches need more headroom.

Is the NVIDIA RTX PRO 6000 MIG 48GB billed per hour or per minute?

Per minute. The hourly rate is divided by 60 and charged for every minute the pod exists. Attached volumes bill per GB-month and continue while a pod is stopped; delete the pod to stop all charges. There is no minimum term or reservation fee.

How do I rent an NVIDIA RTX PRO 6000 MIG 48GB on FastInfra?

Create an account, add prepaid credit, open the GPU configurator and choose the PRO 6000 MIG 48GB, the tier, the GPU count, a container template and storage. The configurator shows the hourly and monthly price, then deploys a pod you reach over SSH or JupyterLab within minutes.

Can I rent multiple PRO 6000 MIG 48GB GPUs in one pod?

Yes, up to 16 per pod. The price scales linearly: 8 GPUs cost $11.15 per hour on Secure.

Is there a cheaper GPU than the PRO 6000 MIG 48GB with the same VRAM?

Yes. The NVIDIA RTX A6000 has 48 GB and starts at $0.357 per hour. It differs in architecture (Ampere), memory bandwidth and multi-GPU interconnect, so compare throughput for your workload before switching.