Balanced cloud GPU for inference and graphics at a moderate price point.
Weekly median price per GPU per hour
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.
USA
11 configs
1x-2x
USA
1 config
1x
USA
1 config
1x
France
1 config
1x
USA
4 configs
1x-8x
USA
3 configs
1x-4x
France
3 configs
1x-4x
USA
12 configs
1x-2x
Singapore
26 configs
1x-8x
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 A10 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) | A10s needed | Cost /hr | Cost /mo |
|---|---|---|---|---|
|
Qwen3.8-27B
27B
|
19 GB
|
1
|
$1.42
|
$1,022
|
Gemma 4 31B
30.7B
|
24 GB
|
2
|
$2.84
|
$2,045
|
GPT-OSS-120B
117B · 5.1B active
|
68 GB
|
4
|
$5.68
|
$4,090
|
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. How we estimate costs.
Nvidia A10 · Per GPU
| Compute · dense | |
|---|---|
| FP16 / BF16 | 125 TFLOPS 250 with sparsity |
| INT8 | 250 TOPS 500 with sparsity |
| FP32 | 31.2 TFLOPS |
| Precision support | FP16BF16TF32FP32INT4INT8 |
| Memory | |
|---|---|
| Capacity | 24 GB GDDR6 |
| Bandwidth | 600 GB/s |
| Bus width | 384-bit |
| ECC | Yes |
| Silicon | |
|---|---|
| Architecture | Ampere |
| Process | Samsung 8N |
| Transistors | 28.3 billion |
| Shader cores | 9,216 CUDA cores |
| Matrix cores | 288 Tensor cores |
| Compute units | 72 SMs |
| Fabric and host | |
|---|---|
| Host interface | PCIe 4.0 x16 |
| Power | |
|---|---|
| Board power | 150 W |
| Cooling | Passive |
Source: official Nvidia A10 datasheet.
As of September 13, 2026, the median on-demand price is $1.42 per GPU per hour across 9 providers.
| Billing type | Configs | Median /GPU/hr | Cheapest |
|---|---|---|---|
On-demand | 32 | $1.42 | $0.20 (in stock, Vast.ai) |
Reserved | 27 | $1.31 | $0.17 (12 mo, in stock, Vast.ai) |
Spot | 3 | $0.60 |
No median for spot: we only show this when at least 3 providers list the GPU on that billing type.
At 720 hours per month, one A10 costs an estimated $1,022 at the median on-demand price. Cheapest verified in stock: $144 per month on-demand, $122 reserved (12 mo).
GetDeploying currently tracks A10 configs from 9 providers. The cheapest verified in-stock on-demand configs come from Vast.ai, Lambda Labs, Sesterce and Runcrate. See the full price comparison above for every provider and config.
As of September 13, 2026, the median on-demand price has been flat over the past 90 days, at about $1.42 per GPU per hour, though it is about 5% below where it was a year ago.
One A10 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 GDDR6 with Ampere Tensor Cores. Good balance of price and performance for inference. Wide cloud availability and mature driver support.
Last updated
