NVIDIA Blackwell, 96 GB GDDR7, PCIe Gen5
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.
Dynamic $0.66/hr · Monthly $299/mo
The RTX 6000 Pro brings next-generation Tensor Cores and 96 GB of GDDR7 memory to a standard PCIe card.
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, offering the widest deployment flexibility.
Hardware AV1 encode and DLSS 4 make the RTX 6000 Pro uniquely capable for AI video inference.
Hourly or monthly, shared or dedicated, plus multi-node clusters.
Full RTX 6000 Pro on shared infrastructure. Launch in minutes, pay by the hour. No commitment.
Deploy Hourly →Same shared RTX 6000 Pro at a flat monthly rate. Predictable billing, cancel anytime.
Deploy Monthly →Scale inference across multiple RTX 6000 Pro nodes with InfiniBand interconnect.
96 GB runs 30B at FP16 and 70B at 4-bit without NVLink, at a fraction of H100 cost.
Blackwell FP8 Tensor Cores and 96 GB enable full fine-tuning of 30B+ models without multi-GPU setups.
Hardware AV1 encode and DLSS 4 make it the best PCIe GPU for AI video generation and rendering.
Blackwell workstation GPU: 96 GB GDDR7, 1.79 TB/s, most memory of any single PCIe GPU.
$0.66/GPU-hour dynamic, $1.25/hr dedicated, or $299/month flat rate.
30B at FP16 natively, 70B at 4-bit. For larger models, use H200 or B200.
No. PCIe Gen5. For multi-GPU NVLink, use H100 or B200.
Yes. Blackwell Tensor Cores with FP8 make it ideal for LoRA, QLoRA, and full fine-tuning of 30B–70B models on a single card.
SSH-ready in under 5 minutes on Dynamic or Dedicated hourly. Multi-node clusters provision in under 1 hour.
The most memory of any PCIe GPU. $0.66/hr dynamic, or $299/mo flat.
On-demand · hourly billing · US & EU regions