96GB · AI Score 45.3/100 · anchored estimate vs 51 measured cards
45.3 AI Score Includes estimates
We have not run NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition on our bench. These figures are anchored estimates, interpolated per workload against the 51 GPUs we did measure. On Llama 3.1 8B (Q4_K_M) NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition should deliver about 245.5 tokens/sec. Stepping up to Qwen3 32B it should hold roughly 66.6 tok/s. The full Llama 3.3 70B still runs, at about 33.1 tok/s. For image generation, SDXL should run near 10.9 it/s, and FLUX.1-dev at 2.52 it/s. 1 of the 12 workloads won't fit on 96GB at the tested precision, Wan 2.2 5B. We publish those as hard gates rather than quietly dropping to a smaller quant.
| Workload | Result | Telemetry | Data |
|---|---|---|---|
| Qwen3 4B | 344.7 tok/s | estimated | Est. |
| Llama 3.1 8B | 245.5 tok/s | estimated | Est. |
| Qwen2.5-Coder 14B | 140.4 tok/s | estimated | Est. |
| Qwen3 32B | 66.6 tok/s | estimated | Est. |
| Llama 3.3 70B | 33.1 tok/s | estimated | Est. |
| Workload | Result | Telemetry | Data |
|---|---|---|---|
| Stable Diffusion XL | 21.8 images/min | estimated | Est. |
| Z-Image Turbo | 12.15 images/min | estimated | Est. |
| FLUX.1 dev | 5.4 images/min | estimated | Est. |
| Workload | Result | Telemetry | Data |
|---|---|---|---|
| FLUX.1 Kontext dev | 2.4 images/min | estimated | Est. |
| Qwen-Image-Edit | 2.06 images/min | estimated | Est. |
| Workload | Result | Telemetry | Data |
|---|---|---|---|
| LTX-Video (distilled) | 12.76 frames/s | estimated | Est. |
| Wan 2.2 5B (720p) | n/a frames/s | estimated | Est. |
| Architecture | Blackwell |
| CUDA cores | 24,064 |
| VRAM | 96GB GDDR7 ECC |
| Memory bus | 512-bit |
| Memory bandwidth | 1792 GB/s |
| Boost clock | 2,617 MHz |
| TDP | 300 W |
| Process | 4nm (TSMC 4N) |
| Interface | PCIe 5.0 x16 |
| Release date | 2025-03-18 |
| Launch MSRP | $8,565 |
NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition scores 45.3/100, #12 of 102. It ran 11 of 12; 1 exceeded its 96GB. Figures are anchored estimates, not measurements, we flag that on every row.
100% = this card, AI & Machine Learning headline metric (AI Score). #2 of 20 desktop cards in this vertical.
| GPU | Relative | % | AI Score |
|---|---|---|---|
| NVIDIA RTX PRO 6000 Blackwell Workstation Edition | 117% | 53.1 | |
| NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition | 100% | 45.3 | |
| NVIDIA RTX PRO 5000 Blackwell | 70% | 31.6 | |
| NVIDIA RTX A6000 | 46% | 21 | |
| NVIDIA RTX PRO 4500 Blackwell | 28% | 12.9 | |
| AMD Radeon Pro W7900 | 28% | 12.8 |
← All AI & Machine Learning GPU rankings
Whole-job timings, composed from our measured per-model results on this card.
| Workflow | Time | Energy | Basis |
|---|---|---|---|
| 24-frame storyboard | 2.3 min | n/a | estimate, 0 of 2 stages measured |
| 60-second AI short film | 2.8 min | n/a | estimate, 0 of 3 stages measured |
| 6-panel comic page | 3.8 min | n/a | estimate, 0 of 3 stages measured |
| Character sheet, 12 poses | 5.2 min | n/a | estimate, 0 of 2 stages measured |
| Full codebase review | 7.1 min | n/a | estimate, 0 of 1 stage measured |
| 20 long-form articles | 14.1 min | n/a | estimate, 0 of 1 stage measured |
| 40-product photo shoot | 18.5 min | n/a | estimate, 0 of 2 stages measured |
| 100-photo restoration batch | 41.7 min | n/a | estimate, 0 of 1 stage measured |