Low-profile Blackwell professional GPU for compact workstations and low-power servers.
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 4000 SFF has 24 GB of VRAM. In practice, that's enough memory for roughly 28B 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) | RTX PRO 4000 SFFs needed | Cost /hr | Cost /mo |
|---|---|---|---|---|
Qwen3.8-27B
27B
|
18 GB
|
1
|
–
|
–
|
Gemma 4 31B
30.7B
|
22 GB
|
1
|
–
|
–
|
GPT-OSS-120B
117B · 5.1B active
|
67 GB
|
4
|
–
|
–
|
GLM-5.3-Flash
320B · 18B active
|
178 GB
|
9
|
–
|
–
|
MiniMax-M3
428B · 23B active
|
239 GB
|
12
|
–
|
–
|
DeepSeek V4.1 Flash
552B · 16B active
|
306 GB
|
15
|
–
|
–
|
Kimi K3
2.8T · 104B active
|
1,544 GB
|
72
|
–
|
–
|
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 4000 SFF · Per GPU
| Compute · dense | |
|---|---|
| FP4 | 385 TFLOPS 770 with sparsity |
| FP8 | 192.5 TFLOPS 385 with sparsity |
| FP16 / BF16 | 96.3 TFLOPS 192.5 with sparsity |
| INT8 | 192.5 TOPS 385 with sparsity |
| FP32 | 24 TFLOPS |
| Precision support | FP4FP8FP16BF16TF32FP32INT8 |
| Memory | |
|---|---|
| Capacity | 24 GB GDDR7 |
| Bandwidth | 432 GB/s |
| Bus width | 192-bit |
| ECC | Yes |
| Silicon | |
|---|---|
| Architecture | Blackwell |
| Process | TSMC 4N |
| Transistors | 45.6 billion |
| Shader cores | 8,960 CUDA cores |
| Matrix cores | 280 Tensor cores |
| Compute units | 70 SMs |
| Fabric and host | |
|---|---|
| Host interface | PCIe 5.0 x8 |
| Power | |
|---|---|
| Board power | 70 W |
| Cooling | Active |
As of November 9, 2026, we track 1 config from 1 provider. Prices are per GPU per hour.
| Billing type | Configs | Cheapest |
|---|---|---|
On-demand | 1 | $0.38 (not verified in stock, Hetzner) |
No median for on-demand: we only show this when at least 3 providers list the GPU on that billing type.
The lowest listed on-demand price for the RTX PRO 4000 SFF is $0.38 per GPU per hour from Hetzner, though we haven't verified current stock.
GetDeploying currently tracks RTX PRO 4000 SFF configs from 1 provider. See the full price comparison above for every provider and config.
One RTX PRO 4000 SFF runs models up to roughly 28B 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 of ECC GDDR7 with Blackwell FP4 Tensor Cores inside a 70W board power limit, so it fits compact systems that cannot supply or cool a full-height card. Suits small-model inference, AI development, rendering and video work.
Models that need more than 24GB of VRAM do not fit on one card, and there is no NVLink to pool memory across cards. The 70W limit also costs throughput: memory bandwidth and single-precision performance run about 35% below the full-height RTX PRO 4000 with the same 24GB. It remains a fit for small-model inference and rendering where power or space is the limit.
Nvidia RTX PRO 4000
24 GB GDDR7 · 56% more bandwidth than the RTX PRO 4000 SFF
Nvidia RTX 4000 SFF Ada
20 GB GDDR6 · 35% less bandwidth than the RTX PRO 4000 SFF
Last updated
