NVIDIA A30 rental pricing
Ampere architecture · 24 GB HBM2e memory · 0.9 TB/s bandwidth · 165 W board power · Released 2021
Price history
Weekly median price per GPU per hour
At a glance
prices checked 1h ago- Lowest published rate
- $0.35/hr
- Sold out everywhere we track · Shadeform
- 90-day trend
- Flat
- Weekly median on-demand, 4 weeks
- Coverage
- 2 providers
- 2 price points
Every provider we track
Cheapest listing per provider and pricing type. Sold-out rows stay so you can see who normally carries it.
Per GPU-hour. Spot, reserved and community pricing differ from on-demand; click through for the provider's current figure.
What can the NVIDIA A30 run?
Memory for the weights plus one sequence of context, how many GPUs hold it, and what that replica costs at the cheapest in-stock on-demand rate.
| Model | Params | Memory | GPUs | $/hr |
|---|---|---|---|---|
| gpt-oss-20b OpenAI | 20.9B· 3.6B active | 20 GiB | 1 | — |
| Gemma 3 27B Google | 27.4B | 26 GiB | 2 | — |
| Qwen3-32B Alibaba | 32.8B | 32 GiB | 2 | — |
| Llama 3.3 70B Instruct Meta | 70.6B | 67 GiB | 4 | — |
| gpt-oss-120b OpenAI | 117B· 5.1B active | 109 GiB | 8 | — |
| Qwen3-235B-A22B Alibaba | 235B· 22.0B active | 220 GiB | 16 | — |
| DeepSeek-R1 DeepSeek | 684B· 37.0B active | 638 GiB | Over 16 | — |
| Kimi K3 Moonshot AI | 2.78T· 104B active | 2.53 TiB | Over 16 | — |
Sized for one sequence at 4K context with 16-bit KV cache and 10% of memory held back. Serving many users at once needs more; the LLM GPU calculator sizes for concurrency and throughput.
NVIDIA A30 pricing questions
How much does it cost to rent a NVIDIA A30 per hour?
Every NVIDIA A30 listing we track is currently sold out. The lowest published rate is $0.35 per GPU-hour from Shadeform.
How much does a NVIDIA A30 cost per month?
Running one NVIDIA A30 around the clock for a month (730 hours) costs about $255 at the cheapest published rate of $0.35 per hour. Reserved terms usually come in below that; ask the provider for a quote.
Are NVIDIA A30 rental prices going up or down?
The weekly median on-demand rate for the NVIDIA A30 has been flat, moving 0.0% over the last 4 weeks, from $0.54 to $0.54 per GPU-hour.
How many cloud providers rent the NVIDIA A30?
We track 2 providers with 2 live prices for the NVIDIA A30. Sold-out listings stay in the table so you can see who normally carries it, but never set the cheapest figure.
What LLMs can you run on one NVIDIA A30?
With 8-bit weights and a single sequence of context, one NVIDIA A30 holds gpt-oss-20b (20.9B). See the model fit table for the full ladder.
Where does this NVIDIA A30 pricing data come from?
Prices are read daily from each provider's public price list or API and recorded whenever they change. Listings are shown per GPU-hour on-demand unless marked otherwise, and the chart covers the last 30 days. The newest listing was checked 1h ago.