Mid-range data center GPU with MIG support for partitioned inference.
Weekly median price per GPU per hour · Get the data
By provider shows one card per company, placed where its best offer ranked. By configuration lists every offer.
What you can rent comes first: in stock, then waitlist, then not reported, then out of stock. Priced offers rank ahead of quote-only, and on-demand ahead of other billing types.
Within a group, five factors set the order:
We match the provider, its country, GPU model, form factor, billing type, availability and instance name. Matching is partial and case-insensitive. Everyday words work too, so "interruptible" finds spot and "sold out" finds out of stock.
No providers match .
Heads up: A provider's own page may quote a different figure, for example on tax, region or a promotion. A monthly-only plan shows a derived hourly rate. Verify before provisioning. More on how we price.
One A30 has 24 GB of VRAM. In practice, that's enough memory for roughly 21B parameters at 4-bit or 6B at 16-bit, assuming a 32K context. Below are some open-weight LLMs, with the estimated memory and GPUs each one needs.
| Model | Memory (INT4 / FP4) | A30s needed | Cost /hr | Cost /mo |
|---|---|---|---|---|
Qwen3.8-27B
27B
|
19 GB
|
1
|
$0.69
|
$497
|
Gemma 4 31B
30.7B
|
24 GB
|
2
|
$1.38
|
$994
|
GPT-OSS-120B
117B · 5.1B active
|
68 GB
|
4
|
$2.76
|
$1,987
|
GLM-5.3-Flash
320B · 18B active
|
178 GB
|
9
|
–
|
–
|
MiniMax-M3
428B · 23B active
|
241 GB
|
12
|
–
|
–
|
DeepSeek V4.1 Flash
552B · 16B active
|
306 GB
|
15
|
–
|
–
|
Kimi K3
2.8T · 104B active
|
1,545 GB
|
72
|
–
|
–
|
Estimates based on the median on-demand rate. Memory is weights plus FP16/BF16 KV cache at 32K context per request. GPU counts assume 90% of advertised VRAM is usable. No guarantee of runtime support, usable performance, or that a matching quantized build exists. Pricing methodology.
Nvidia A30 · Per GPU
| Compute · dense | |
|---|---|
| FP16 / BF16 | 165 TFLOPS 330 with sparsity |
| INT8 | 330 TOPS 661 with sparsity |
| FP32 | 10.3 TFLOPS |
| FP64 | 5.2 TFLOPS |
| Precision support | FP16BF16TF32FP32FP64INT4INT8 |
| Memory | |
|---|---|
| Capacity | 24 GB HBM2 |
| Bandwidth | 933 GB/s |
| ECC | Yes |
| Silicon | |
|---|---|
| Architecture | Ampere |
| Process | TSMC N7 |
| Transistors | 54.2 billion |
| Shader cores | 3,584 CUDA cores |
| Matrix cores | 224 Tensor cores |
| Compute units | 56 SMs |
| Fabric and host | |
|---|---|
| Host interface | PCIe 4.0 x16 |
| Power | |
|---|---|
| Board power | 165 W |
| Cooling | Passive |
| Platform | |
|---|---|
| Partitioning | MIG, up to 4 instances |
Source: official Nvidia A30 datasheet.
As of September 27, 2026, the median on-demand price is $0.69 per GPU per hour across 3 providers with a priced on-demand config.
| Billing type | Configs | Median /GPU/hr | Cheapest |
|---|---|---|---|
On-demand | 20 | $0.69 | $0.41 (in stock, Jarvislabs) |
Reserved | 27 | $0.58 | $0.38 (12 mo, in stock, Jarvislabs) |
Spot | 3 | $0.29 (in stock, Jarvislabs) |
No median for spot: we only show this when at least 3 providers list the GPU on that billing type.
The cheapest verified in-stock on-demand A30 tracked by GetDeploying is $0.41 per GPU per hour from Jarvislabs. Cheapest verified in stock on other billing types: reserved $0.38 (12 mo) and spot $0.29, also from Jarvislabs.
At 720 hours per month, one A30 costs an estimated $497 at the median on-demand price. Cheapest verified in stock: $295 per month on-demand, $274 reserved (12 mo), $209 spot.
GetDeploying currently tracks A30 configs from 8 providers. Jarvislabs has verified in-stock on-demand configs. See the full price comparison above for every provider and config.
One A30 runs models up to roughly 21B parameters at 4-bit quantization or 6B at 16-bit, assuming a 32K context. Larger models run across multiple GPUs: the model table above shows the estimated memory and GPU count for popular open-weight LLMs.
24GB HBM2e with higher memory bandwidth than GDDR6 alternatives. Supports FP64 for mixed AI and scientific workloads. MIG support for partitioning into smaller instances.
PCIe-only. 24GB VRAM is limiting for larger models. The L40S offers more VRAM (48GB) and FP8 at a similar price point for pure inference.
Nvidia L40S
48 GB GDDR6 · released Q3 2023
Nvidia L4
24 GB GDDR6 · 68% less bandwidth than the A30
Nvidia A10
24 GB GDDR6 · 36% less bandwidth than the A30
Last updated
