Nvidia A30 cloud rental prices
2 providers list the Nvidia A30, 0 have it in stock. Prices run from $0.10 to $0.35 per GPU hour — the same card, 3.5x apart.
Prices and stock checked 2 hours ago
What it costs you to run
Estimated at the cheapest listed rate of $0.10/GPU/hr (Lium), per GPU, before storage, egress or commitment discounts.
Renting at the median instead of the floor costs you an extra $91 a month per GPU. That is 56% of the bill, for identical silicon.
Every provider renting the Nvidia A30
Ordered strictly by entry price per GPU hour. Rows above the median are marked. Stock is what the provider reported at our last check, not a guarantee.
| Provider | Country | Configs | Scale | From | Spot | Reserved | Stock | Grab |
|---|---|---|---|---|---|---|---|---|
| Lium | — | 1 | 1x-1x | $0.10 | — | — | Out of stock | GrabLium — opens the provider's site |
| Massed Compute | United States of America | 8 | 1x-8x | $0.35 | — | — | Out of stock | GrabMassed Compute — opens the provider's site |
Live inventory signal
The Lium marketplace publishes GPU counts, which almost nobody else does. It holds 0 Nvidia A30 GPUs at $0.10/GPU/hr, with 0% already rented. There is slack at that price today.
All 9 configurations
| Configuration | Provider | Region | VRAM | vCPU | RAM | Billing | Per GPU/hr | Total/hr | Stock |
|---|---|---|---|---|---|---|---|---|---|
| 1x NVIDIA A30 | Lium | — | — | — | — | On-Demand | $0.10 | $0.10 | Out of stock |
| 1x A30 | Massed Compute | desmoines-usa-1 | 24 GB | 16 | 48 GB | On-Demand | $0.35 | $0.35 | Out of stock |
| 1x A30 | Massed Compute | wichita-usa-1 | 24 GB | 16 | 48 GB | On-Demand | $0.35 | $0.35 | Out of stock |
| 2x A30 | Massed Compute | desmoines-usa-1 | 48 GB | 30 | 96 GB | On-Demand | $0.35 | $0.70 | Out of stock |
| 2x A30 | Massed Compute | wichita-usa-1 | 48 GB | 30 | 96 GB | On-Demand | $0.35 | $0.70 | Out of stock |
| 8x A30 | Massed Compute | desmoines-usa-1 | 192 GB | 94 | 384 GB | On-Demand | $0.35 | $2.80 | Out of stock |
| 8x A30 | Massed Compute | wichita-usa-1 | 192 GB | 94 | 384 GB | On-Demand | $0.35 | $2.80 | Out of stock |
| 4x A30 | Massed Compute | desmoines-usa-1 | 96 GB | 50 | 192 GB | On-Demand | $0.35 | $1.40 | Out of stock |
| 4x A30 | Massed Compute | wichita-usa-1 | 96 GB | 50 | 192 GB | On-Demand | $0.35 | $1.40 | Out of stock |
What fits in 24 GB
The question behind most rentals: will the model load. Sized against one Nvidia A30.
| Model | 16-bit | 8-bit | 4-bit |
|---|---|---|---|
| DeepSeek-V3 DeepSeek · 671B params · 37B active | 1,610 GB 68× · 22 GB free | 805 GB 34× · 11 GB free | 403 GB 17× · 5 GB free |
| Llama 3.1 405B Meta · 405B params | 972 GB 41× · 12 GB free | 486 GB 21× · 18 GB free | 243 GB 11× · 21 GB free |
| Qwen3 235B-A22B Alibaba · 235B params · 22B active | 564 GB 24× · 12 GB free | 282 GB 12× · 6 GB free | 141 GB 6× · 3 GB free |
| Mixtral 8x22B Mistral · 141B params · 39B active | 338 GB 15× · 22 GB free | 169 GB 8× · 23 GB free | 85 GB 4× · 11 GB free |
| Mistral Large 2 Mistral · 123B params | 295 GB 13× · 17 GB free | 148 GB 7× · 20 GB free | 74 GB 4× · 22 GB free |
| gpt-oss-120b OpenAI · 117B params · 5.1B active | 281 GB 12× · 7 GB free | 140 GB 6× · 4 GB free | 70 GB 3× · 2 GB free |
| Qwen2.5 72B Alibaba · 72.7B params | 174 GB 8× · 18 GB free | 87 GB 4× · 9 GB free | 44 GB 2× · 4 GB free |
| Llama 3.3 70B Meta · 70.6B params | 169 GB 8× · 23 GB free | 85 GB 4× · 11 GB free | 42 GB 2× · 6 GB free |
| Qwen3 32B Alibaba · 32.8B params | 79 GB 4× · 17 GB free | 39 GB 2× · 9 GB free | 20 GB 1× · 4 GB free |
| Gemma 2 27B Google · 27.2B params | 65 GB 3× · 7 GB free | 33 GB 2× · 15 GB free | 16 GB 1× · 8 GB free |
| Mistral Small 3 Mistral · 24B params | 58 GB 3× · 14 GB free | 29 GB 2× · 19 GB free | 14 GB 1× · 10 GB free |
| Llama 3.1 8B Meta · 8B params | 19 GB 1× · 5 GB free | 10 GB 1× · 14 GB free | 5 GB 1× · 19 GB free |
Required memory is weights plus 20% for KV cache and runtime at short context; long contexts and large batches need more. Cells tinted green fit on a single Nvidia A30.
Nvidia A30 specifications
| Architecture | Ampere |
|---|---|
| Memory per GPU | 24 GB HBM2 |
| Memory bandwidth | 933 GB/s |
| Release date | Q2 2021 |
| FP16 / BF16 compute rate | 165 TFLOPS (dense), 330 with sparsity |
| INT8 compute rate | 330 TOPS (dense), 661 with sparsity |
| Process node | TSMC N7 |
| Board power | 165 W |
| Partitioning | MIG, up to 4 instances |
Frequently asked questions
How much does it cost to rent a Nvidia A30 per hour?
As of September 6, 2026 the Nvidia A30 rents from $0.10 per GPU per hour at Lium. The median across 2 providers is $0.22 and the dearest listing asks $0.35.
Who is the cheapest Nvidia A30 provider right now?
Lium at $0.10 per GPU per hour. That is 56% under the median of $0.22, so renting from a mid-priced provider costs you $0.12 an hour more for the same silicon.
What does a Nvidia A30 cost per month?
At the cheapest listed rate of $0.10 per GPU per hour, one Nvidia A30 running non-stop for a 730-hour month costs $73. At the median rate it costs $164.
Can I actually get a Nvidia A30 today?
Not from the providers we track. None of the 2 providers listing the Nvidia A30 confirmed stock at the last check, which is why the headline price is lower than what you will really pay.
How much VRAM does the Nvidia A30 have?
24 GB HBM2 per board. That holds a model of roughly 9 billion parameters at 16-bit, or about 19 billion at 8-bit, before context and activations.
What architecture is the Nvidia A30, and when did it launch?
Ampere, released Q2 2021. 2 cloud providers publish a price for it.