Compact entry-level Blackwell workstation GPU for professional visualization and light 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 RTX PRO 2000 has 16 GB of VRAM. In practice, that's enough memory for roughly 15B parameters at 4-bit or 2B 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 PRO 2000s needed | Cost /hr | Cost /mo |
|---|---|---|---|---|
Qwen3.8-27B
27B
|
18 GB
|
2
|
–
|
–
|
Gemma 4 31B
30.7B
|
22 GB
|
2
|
–
|
–
|
GPT-OSS-120B
117B · 5.1B active
|
67 GB
|
5
|
–
|
–
|
GLM-5.3-Flash
320B · 18B active
|
178 GB
|
13
|
–
|
–
|
MiniMax-M3
428B · 23B active
|
239 GB
|
17
|
–
|
–
|
DeepSeek V4.1 Flash
552B · 16B active
|
306 GB
|
22
|
–
|
–
|
Kimi K3
2.8T · 104B active
|
1,544 GB
|
108
|
–
|
–
|
Estimates based on the median on-demand rate. Memory is weights plus FP8 KV cache at 32K context per request (FP16/BF16 in the 16-bit column). 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 RTX PRO 2000 · Per GPU
| Compute · dense | |
|---|---|
| FP4 | 272.5 TFLOPS 545 with sparsity |
| FP8 | 136.3 TFLOPS 272.5 with sparsity |
| FP16 / BF16 | 68.1 TFLOPS 136.3 with sparsity |
| INT8 | 136.3 TOPS 272.5 with sparsity |
| FP32 | 17 TFLOPS |
| Precision support | FP4FP8FP16BF16TF32FP32INT8 |
| Memory | |
|---|---|
| Capacity | 16 GB GDDR7 |
| Bandwidth | 288 GB/s |
| Bus width | 128-bit |
| ECC | Yes |
| Silicon | |
|---|---|
| Architecture | Blackwell |
| Process | TSMC 4N |
| Transistors | 21.9 billion |
| Shader cores | 4,352 CUDA cores |
| Matrix cores | 136 Tensor cores |
| Compute units | 34 SMs |
| Fabric and host | |
|---|---|
| Host interface | PCIe 5.0 x8 |
| Power | |
|---|---|
| Board power | 70 W |
| Cooling | Active |
As of September 28, 2026, we track 4 configs from 1 provider, none of them on demand. Prices are per GPU per hour.
| Billing type | Configs | Cheapest |
|---|---|---|
Reserved | 4 | $0.16 (24 mo) |
No median for reserved: we only show this when at least 3 providers list the GPU on that billing type.
GetDeploying currently tracks RTX PRO 2000 configs from 1 provider. See the full price comparison above for every provider and config.
One RTX PRO 2000 runs models up to roughly 15B parameters at 4-bit quantization or 2B 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.
16GB of ECC GDDR7 with Blackwell FP4 Tensor Cores in a 70W dual-slot card that needs no supplementary power connector. Suits compact workstations and low-power cloud instances running CAD, 3D visualization, video encoding, and small-model inference.
128-bit memory bus and 288 GB/s bandwidth limit throughput on larger models, and PCIe 5.0 x8 halves the usual host bandwidth. For heavier compute or models beyond 16GB, consider the RTX PRO 4000 with 24GB and roughly double the single-precision throughput.
Nvidia L4
24 GB GDDR6 · data center card
Nvidia RTX PRO 4000
24 GB GDDR7 · 2.3x the bandwidth of the RTX PRO 2000
Nvidia A4000
16 GB GDDR6 · 56% more bandwidth than the RTX PRO 2000
Last updated
