What can I run on RTX PRO 6000 Blackwell Server?
96 GB VRAMBlackwellFP4 Tensor Core 4 PFLOPSUp to 600W (configurable)View matrix for this target →
Server (passively cooled) edition with 96 GB GDDR7. The RTX PRO 6000 Blackwell Workstation and Max-Q editions are different SKUs. Hugging Face Jobs lists an "Nvidia RTX PRO 6000" flavor (96 GB); its edition is not stated there.
Policy by policy
| Policy | Params | Inference memory (sourced, with precision) | On RTX PRO 6000 Blackwell Server | Best measured |
|---|---|---|---|---|
| GR00T N1.7 VLA | 3B | ≥16 GB | measured | 40.49 Hz · TensorRT · bf16 · 2 cam |
| ACT Imitation | 80M | 211 MB measured fp32 | no data | |
| Diffusion Policy Imitation | — | 1.12 GB measured fp32 | no data | |
| EO-1 VLA | 3B | ≥6.5 GB | no data | |
| Evo-1 VLA | 770M | — | no data | |
| Fast-WAM World model | 6B | — | no data | |
| HIL-SERL RL | — | — | no data | |
| LingBot-VA World model | 5.3B | ≥18 GB | no data | |
| MolmoAct2 VLA | — | 12.1 GB measured bf16 | no data | |
| Multitask DiT Imitation | 450M | — | no data | |
| OpenVLA VLA | 7.5B | 15 GB measured bf16 | no data | |
| OpenVLA-OFT VLA | — | ≥16 GB | no data | |
| SmolVLA VLA | 450M | 1.75 GB measured fp32 | no data | |
| TD-MPC RL | — | — | no data | |
| VLA-JEPA VLA | — | — | no data | |
| VQ-BeT Imitation | — | — | no data | |
| WALL-OSS VLA | — | — | no data | |
| X-VLA VLA | 900M | — | no data | |
| π0 VLA | 3.3B | 13.32 GB measured fp32 | no data | |
| π0-FAST VLA | — | ≥8 GB | no data | |
| π0.5 VLA | — | ≥8 GB | no data |
“Exceeds memory” compares a policy's upstream-stated minimum inference memory (never a measured peak, which is precision-specific) with this target's VRAM. It is arithmetic, not observation, and is labelled inferred. Quantised or split runtimes can change the answer; a measured run always wins.
All measured runs on RTX PRO 6000 Blackwell Server
| Policy | Runtime | Precision | Cams | p50 / p95 ms | Inference | Platform | Source |
|---|---|---|---|---|---|---|---|
| GR00T N1.7 | TensorRT | bf16 | 2 @256x256 | 24.7 / — | 40.49 Hz | —conditionstorch_threads: 8 intra-op / 1 inter-op Inference cost only; not task success. Median of 60 timed calls (3 repetitions x 20 after 10 warmup), fixed inputs, includes preprocessing and action decoding, excludes RPC. Precision is the repo default (unquantized BF16). | T3 · community reported |
| GR00T N1.7 | torch.compile | bf16 | 2 @256x256 | 52.1 / — | 19.19 Hz | —conditionstorch_threads: 8 intra-op / 1 inter-op Inference cost only; not task success. Median of 60 timed calls (3 repetitions x 20 after 10 warmup), fixed inputs, includes preprocessing and action decoding, excludes RPC. Precision is the repo default (unquantized BF16). | T3 · community reported |
| GR00T N1.7 | PyTorch eager | bf16 | 2 @256x256 | 75.7 / — | 13.21 Hz | —conditionstorch_threads: 8 intra-op / 1 inter-op Inference cost only; not task success. Median of 60 timed calls (3 repetitions x 20 after 10 warmup), fixed inputs, includes preprocessing and action decoding, excludes RPC. Precision is the repo default (unquantized BF16). | T3 · community reported |
Sources
- T1 · upstream documentedvendor-docsverified 2026-10-24 (1d ago)
RTX PRO 6000 Blackwell Server Edition spec table: Blackwell, FP4 4 PFLOPS, FP16/BF16 1 PFLOP.
“GPU Architecture NVIDIA Blackwell Architecture CUDA Parallel Processing Cores 24,064 NVIDIA RT Cores 188 (4th Gen) FP4 Tensor Core 4 PFLOPS FP8 Tensor Core 2 PFLOPS FP16 | BF16 Tensor Core 1 PFLOP”
https://www.nvidia.com/en-us/data-center/rtx-pro-6000-blackwell-server-edition/ - T1 · upstream documentedvendor-docsverified 2026-10-24 (1d ago)
Quick specs: 96GB GDDR7 with ECC, max power up to 600W.
“GPU Memory 96GB GDDR7 with ECC Display Ports 4x DisplayPort 2.1 Max Power Consumption Up to 600W (configurable)”
https://www.nvidia.com/en-us/data-center/rtx-pro-6000-blackwell-server-edition/