The NVIDIA RTX 6000 Pro is a Blackwell-generation workstation GPU with 96 GB of GDDR7 memory and 1.79 TB/s of bandwidth, the most memory of any PCIe GPU. It runs 30B–70B models natively without quantisation, making it ideal for development, fine-tuning, and cost-efficient inference. Available on packet.ai from $0.66/GPU-hour.
The RTX 6000 Pro brings Blackwell Tensor Cores and 96 GB of GDDR7 to a standard PCIe card, the most accessible path to next-generation GPU compute.
Next-gen Tensor Cores with FP4 and FP8 support, Blackwell inference in PCIe form factor for the first time.
96 GB GDDR7 runs 30B models at FP16 and 70B at 4-bit, on a single PCIe card, no NVLink required.
Drops into any Gen5 server without SXM motherboards, widest deployment flexibility.
Hardware AV1 encode and DLSS 4 make the RTX 6000 Pro uniquely capable for AI video inference.
96 GB runs 30B at FP16 and 70B at 4-bit, without NVLink, at a fraction of H100 cost.
Fine-tune 30B–70B on a single card without quantisation.
AV1 hardware encode and DLSS 4 make the RTX 6000 Pro the best GPU for video generation.
| Configuration | On-Demand | Monthly | 3 Months | 6 Months | Annually |
|---|---|---|---|---|---|
| Dynamic | Dynamic only | ||||
| 1× NVIDIA RTX 6000 ProMost Popular | $0.66/hr | $299/mo $0.41/hr eff. | $897/3mo | $1,794/6mo | $3,588/yr |
The RTX 6000 Pro is a Blackwell-generation workstation GPU with 96 GB of GDDR7 and 1.79 TB/s bandwidth, most memory of any single PCIe GPU.
RTX 6000 Pro starts at $0.66/GPU-hour dynamic, or $299/month flat.
30B at FP16 and 70B at 4-bit on a single card. For full FP16 70B, use H200 or B200.
No, PCIe Gen5. For multi-GPU NVLink, use H100 or B200.
RTX 6000 Pro has 2× more memory (96 GB vs 48 GB) and 2× more bandwidth at a similar price.
The most memory of any PCIe GPU. $0.66/hr dynamic, or $299/mo flat.
On-demand · hourly billing · US & EU regions