What can NVIDIA RTX PRO 6000 Blackwell run?
Build: NVIDIA RTX PRO 6000 Blackwell + — + 32 GB RAM (windows)
Runs comfortably264 models
Full-VRAM resident, with room for context. No compromises.
Quant: Q4_K_MContext: 8,192VRAM: 2.4 GBHeadroom: 93.6 GB3215tok/sEstimated
Quant: Q4_K_MContext: 2,048VRAM: 83.7 GBHeadroom: 12.3 GBollama run llama4:scout18tok/sEstimated
ollama run llama4:scoutQuant: FP16Context: 8,192VRAM: 19.8 GBHeadroom: 76.2 GBollama run llama3.1:8b73tok/sEstimated
ollama run llama3.1:8bQuant: Q8_0Context: 8,192VRAM: 50.4 GBHeadroom: 45.6 GBollama run qwen3:30b37tok/sEstimated
ollama run qwen3:30bQuant: Q8_0Context: 8,192VRAM: 39.7 GBHeadroom: 56.3 GBollama run qwen2.5-coder:32b34tok/sEstimated
ollama run qwen2.5-coder:32bQuant: Q4_K_MContext: 8,192VRAM: 33.2 GBHeadroom: 62.8 GBollama run qwen3.6:27b71tok/sEstimated
ollama run qwen3.6:27bQuant: Q8_0Context: 8,192VRAM: 78.0 GBHeadroom: 18.0 GBollama run llama3.3:70b16tok/sEstimated
ollama run llama3.3:70bQuant: Q8_0Context: 8,192VRAM: 53.5 GBHeadroom: 42.5 GBollama run qwen3:32b34tok/sEstimated
ollama run qwen3:32bQuant: Q8_0Context: 8,192VRAM: 52.0 GBHeadroom: 44.0 GBollama run gemma4:31b35tok/sEstimated
ollama run gemma4:31bQuant: Q8_0Context: 8,192VRAM: 14.4 GBHeadroom: 81.6 GBollama run qwen3:8b137tok/sEstimated
ollama run qwen3:8bQuant: 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 qwen3.5:9bRuns with tradeoffs7 models
Tight VRAM, partial CPU offload, or context-limited.
Quant: Q4_K_MContext: 2,048VRAM: 92.4 GBHeadroom: 3.6 GB- • Tight VRAM fit — only 3.6 GB headroom left for context growth
ollama run nemotron3:super16tok/sEstimated
- • Tight VRAM fit — only 3.6 GB headroom left for context growth
ollama run nemotron3:superQuant: Q4_K_MContext: 2,048VRAM: 93.8 GBHeadroom: 2.2 GB- • Tight VRAM fit — only 2.2 GB headroom left for context growth
ollama run mistral-large:123b16tok/sEstimated
- • Tight VRAM fit — only 2.2 GB headroom left for context growth
ollama run mistral-large:123bQuant: Q4_K_MContext: 2,048VRAM: 107.6 GBHeadroom: 7.6 GB- • Partial CPU offload: ~11% of layers run on CPU
ollama run mixtral:8x22b14tok/sEstimated
- • Partial CPU offload: ~11% of layers run on CPU
ollama run mixtral:8x22bQuant: Q4_K_MContext: 2,048VRAM: 107.6 GBHeadroom: 7.6 GB- • Partial CPU offload: ~11% of layers run on CPU
14tok/sEstimated
- • Partial CPU offload: ~11% of layers run on CPU
Quant: Q4_K_MContext: 2,048VRAM: 97.1 GBHeadroom: 18.1 GB- • Partial CPU offload: ~1% of layers run on CPU
54tok/sEstimated
- • Partial CPU offload: ~1% of layers run on CPU
Quant: AWQ-INT4Context: 2,048VRAM: 97.1 GBHeadroom: 18.1 GB- • Partial CPU offload: ~1% of layers run on CPU
32tok/sEstimated
- • Partial CPU offload: ~1% of layers run on CPU
Quant: AWQ-INT4Context: 2,048VRAM: 105.9 GBHeadroom: 9.3 GB- • Partial CPU offload: ~9% of layers run on CPU
73tok/sEstimated
- • Partial CPU offload: ~9% of layers run on CPU
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: 7 new tradeoff
- • Nemotron 3 Super (120B-A12B)
- • Mistral Large 2 (123B)
- • Mixtral 8x22B Instruct
- • WizardLM-2 8x22B
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: 5 new comfortable
- • Mixtral 8x22B Instruct
- • WizardLM-2 8x22B
- • DBRX Base
- • DBRX Instruct
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: 14 new comfortable
- • Qwen 3 235B-A22B
- • GLM-5
- • Nemotron 3 Super (120B-A12B)
- • Llama 3.1 Nemotron Ultra 253B
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 (19 GB) combined.
—
Even with CPU offload, needs more memory than your VRAM (96 GB) + 60% of system RAM (19 GB) combined.
Even with CPU offload, needs more memory than your VRAM (96 GB) + 60% of system RAM (19 GB) combined.
—
Even with CPU offload, needs more memory than your VRAM (96 GB) + 60% of system RAM (19 GB) combined.
Even with CPU offload, needs more memory than your VRAM (96 GB) + 60% of system RAM (19 GB) combined.
—
Even with CPU offload, needs more memory than your VRAM (96 GB) + 60% of system RAM (19 GB) combined.
Even with CPU offload, needs more memory than your VRAM (96 GB) + 60% of system RAM (19 GB) combined.
—
Even with CPU offload, needs more memory than your VRAM (96 GB) + 60% of system RAM (19 GB) combined.
Even with CPU offload, needs more memory than your VRAM (96 GB) + 60% of system RAM (19 GB) combined.
—
Even with CPU offload, needs more memory than your VRAM (96 GB) + 60% of system RAM (19 GB) combined.
How to read these numbers
Want a specific benchmark we don't have? Email Contact support and we'll prioritize it.