Professional workstation GPU for AI development and CAD.
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
1 config
1x
USA
1 config
1x
USA
19 configs
1x-8x
USA
4 configs
1x-8x
USA
32 configs
1x-8x
USA
3 configs
1x-8x
France
26 configs
1x-8x
France
1 config
1x
USA
3 configs
1x-4x
UAE
4 configs
1x-8x
Singapore
4 configs
1x-2x
Finland
28 configs
1x-8x
USA
1 config
1x
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 RTX A6000 has 48 GB of VRAM. In practice, that's enough memory for roughly 60B parameters at 4-bit or 17B 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) | RTX A6000s needed | Cost /hr | Cost /mo |
|---|---|---|---|---|
Qwen3.8-27B
27B
|
19 GB
|
1
|
$0.56
|
$403
|
Gemma 4 31B
30.7B
|
24 GB
|
1
|
$0.56
|
$403
|
GPT-OSS-120B
117B · 5.1B active
|
68 GB
|
2
|
$1.12
|
$806
|
GLM-5.3-Flash
320B · 18B active
|
178 GB
|
8
|
$4.48
|
$3,226
|
MiniMax-M3
428B · 23B active
|
241 GB
|
8
|
$4.48
|
$3,226
|
DeepSeek V4.1 Flash
552B · 16B active
|
306 GB
|
8
|
$4.48
|
$3,226
|
Kimi K3
2.8T · 104B active
|
1,545 GB
|
36
|
–
|
–
|
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 RTX A6000 · Per GPU
| Compute · dense | |
|---|---|
| FP16 / BF16 | 154.8 TFLOPS 309.6 with sparsity |
| INT8 | 309.7 TOPS 619.4 with sparsity |
| FP32 | 38.7 TFLOPS |
| Precision support | FP16BF16TF32FP32INT4INT8 |
| Memory | |
|---|---|
| Capacity | 48 GB GDDR6 |
| Bandwidth | 768 GB/s |
| Bus width | 384-bit |
| ECC | Yes |
| Silicon | |
|---|---|
| Architecture | Ampere |
| Process | Samsung 8N |
| Transistors | 28.3 billion |
| Shader cores | 10,752 CUDA cores |
| Matrix cores | 336 Tensor cores |
| Compute units | 84 SMs |
| Fabric and host | |
|---|---|
| GPU interconnect | NVLink 112 GB/s |
| Host interface | PCIe 4.0 x16 |
| Power | |
|---|---|
| Board power | 300 W |
| Cooling | Active |
Source: official Nvidia RTX A6000 datasheet.
As of September 12, 2026, the median on-demand price is $0.56 per GPU per hour across 17 providers with a priced on-demand config.
| Billing type | Configs | Median /GPU/hr | Cheapest |
|---|---|---|---|
On-demand | 79 | $0.56 | $0.35 (in stock, Thunder Compute) |
Reserved | 71 | $0.54 | $0.35 |
Spot | 13 | $0.40 | $0.30 (in stock, Verda) |
The cheapest verified in-stock on-demand RTX A6000 tracked by GetDeploying is $0.35 per GPU per hour from Thunder Compute. Cheapest verified in stock on other billing types: spot $0.30 from Verda.
At 720 hours per month, one RTX A6000 costs an estimated $403 at the median on-demand price. Cheapest verified in stock: $252 per month on-demand, $216 spot.
GetDeploying currently tracks RTX A6000 configs from 20 providers. The cheapest verified in-stock on-demand configs come from Thunder Compute, GPU.ai, Lium and Runpod. See the full price comparison above for every provider and config.
As of September 12, 2026, the median on-demand price has been flat over the past 90 days, at about $0.56 per GPU per hour.
One RTX A6000 runs models up to roughly 60B parameters at 4-bit quantization or 17B 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.
48GB GDDR6 with NVLink (112 GB/s). Professional-grade with ECC memory and ISV certifications. Strong for both AI development and CAD/visualization workloads.
Priced as a professional workstation GPU. For pure AI inference, the L40S offers similar VRAM with better FP8 performance at lower cost.
Last updated
