What can NVIDIA RTX PRO 6000 Blackwell run for vision?
Build: RTX PRO 6000 Blackwell + Threadripper PRO + 128GB
Runs comfortably37 models
Ranked by fit for vision use case + predicted speed. Click a row for VRAM breakdown.
Quant: Q4_K_MContext: 8,192VRAM: 15.8 GBHeadroom: 80.2 GBollama run gemma4:12b161tok/sEstimated
ollama run gemma4:12bQuant: Q4_K_MContext: 8,192VRAM: 13.2 GBHeadroom: 82.8 GBollama run qwen3.5:9b214tok/sEstimated
ollama run qwen3.5:9bQuant: Q8_0Context: 8,192VRAM: 8.4 GBHeadroom: 87.6 GBollama run gemma4:e4b274tok/sEstimated
ollama run gemma4:e4bQuant: Q4_K_MContext: 8,192VRAM: 18.4 GBHeadroom: 77.6 GBollama run ministral-3:14b138tok/sEstimated
ollama run ministral-3:14bQuant: Q8_0Context: 8,192VRAM: 8.4 GBHeadroom: 87.6 GBollama run gemma3:4b274tok/sEstimated
ollama run gemma3:4bQuant: Q8_0Context: 8,192VRAM: 5.1 GBHeadroom: 90.9 GBollama run gemma4:e2b548tok/sEstimated
ollama run gemma4:e2bQuant: Q4_K_MContext: 8,192VRAM: 6.5 GBHeadroom: 89.5 GB459tok/sEstimated
Quant: BF16Context: 8,192VRAM: 9.6 GBHeadroom: 86.4 GB194tok/sEstimated
Quant: Q4_K_MContext: 8,192VRAM: 10.0 GBHeadroom: 86.0 GB276tok/sEstimated
Quant: Q4_K_MContext: 8,192VRAM: 18.3 GBHeadroom: 77.7 GB138tok/sEstimated
Quant: Q4_K_MContext: 8,192VRAM: 10.0 GBHeadroom: 86.0 GB276tok/sEstimated
Quant: Q4_K_MContext: 2,048VRAM: 3.3 GBHeadroom: 92.7 GB1015tok/sEstimated
What if you upgraded?
Hypothetical scenarios. We re-ran the compatibility engine for each.
+32 GB system RAM
~$80–150
Doubles your CPU-offload working set. Helps when models don't quite fit in VRAM.
Unlocks: 227 new comfortable, 14 new tradeoff
- • Qwen 3 0.6B
- • Llama 4 Scout
- • Llama 3.1 8B Instruct
- • Qwen 3 30B-A3B
Upgrade to NVIDIA H200 NVL (PCIe)
~$32000
141 GB VRAM (vs your 96 GB) plus a bandwidth jump from ~1792 GB/s to ~4800 GB/s.
Unlocks: 232 new comfortable
- • Qwen 3 0.6B
- • Llama 4 Scout
- • Llama 3.1 8B Instruct
- • Qwen 3 30B-A3B
Add a second NVIDIA RTX PRO 6000 Blackwell
~$8999
Tensor parallelism splits the model across both cards, effectively doubling VRAM. Bandwidth doesn't double — runs ~1.5× the single-card speed in practice.
Unlocks: 241 new comfortable
- • Qwen 3 235B-A22B
- • Qwen 3 0.6B
- • Llama 4 Scout
- • Llama 3.1 8B Instruct
Some links above are affiliate links. We may earn a commission at no extra cost to you. How we make money.
Won't runtop 5 popular models
Need more memory than you have. Shown for orientation.
Even with CPU offload, needs more memory than your VRAM (96 GB) + 60% of system RAM (77 GB) combined.
—
Even with CPU offload, needs more memory than your VRAM (96 GB) + 60% of system RAM (77 GB) combined.
Even with CPU offload, needs more memory than your VRAM (96 GB) + 60% of system RAM (77 GB) combined.
—
Even with CPU offload, needs more memory than your VRAM (96 GB) + 60% of system RAM (77 GB) combined.
Even with CPU offload, needs more memory than your VRAM (96 GB) + 60% of system RAM (77 GB) combined.
—
Even with CPU offload, needs more memory than your VRAM (96 GB) + 60% of system RAM (77 GB) combined.
Even with CPU offload, needs more memory than your VRAM (96 GB) + 60% of system RAM (77 GB) combined.
—
Even with CPU offload, needs more memory than your VRAM (96 GB) + 60% of system RAM (77 GB) combined.
Even with CPU offload, needs more memory than your VRAM (96 GB) + 60% of system RAM (77 GB) combined.
—
Even with CPU offload, needs more memory than your VRAM (96 GB) + 60% of system RAM (77 GB) combined.
How to read these numbers
Want a specific benchmark we don't have? Email Contact support and we'll prioritize it.