RTX A2000 cloud pricing, August 2026
Live RTX A2000 quotes (6 GB VRAM) across the providers we track, cheapest first. Marketplace prices are real asks from the Vast.ai order book; secure/on-demand tiers carry datacenter SLAs (what the tiers mean).
Quotes refreshed 2026-08-23| Provider | Tier | $/hr per GPU | Median $/hr | Live offers | |
|---|---|---|---|---|---|
| RunPod | community | $0.120 | - | - | Rent |
| RunPod | secure | $0.500 | - | - | Rent |
What fits on a single RTX A2000
Models from our tracked open-weight set that fit in 6 GB, with KV-cache headroom included. Bigger models need multi-GPU nodes (math in the calculator).
| Model | Params | Fits at | VRAM needed | Cheapest API $/1M out |
|---|---|---|---|---|
| Llama 3.2 3B | 3.2B | FP8 | 5 GB | compare → |
| Llama 3.1 8B | 8B | INT4 | 6 GB | compare → |
FAQ
How much does it cost to rent a RTX A2000?
As of 2026-08-23, RTX A2000 rentals start at $0.120/hr (community tier at RunPod). Datacenter capacity with SLAs typically costs more than community or marketplace hardware.
What can you run on a RTX A2000?
With 6 GB of VRAM, a single RTX A2000 fits models up to roughly 4B parameters at FP8 or 8B at INT4 quantization, including KV-cache headroom.
Cite or embed today's floor
Live badge for a README. It updates itself with every daily refresh:
[](https://llmhosting.ai/gpus/rtx-a2000)
Citation: RTX A2000 rental floor $0.120/hr (llmhosting.ai, 2026-08-23). Free to reuse with a link back.