What can NVIDIA RTX PRO 6000 Blackwell run for chat?
Build: RTX PRO 6000 Blackwell + Threadripper PRO + 128GB
Runs comfortably255 models
Ranked by fit for chat use case + predicted speed. Click a row for VRAM breakdown.
Quant: Q4_K_MContext: 8,192VRAM: 2.4 GBHeadroom: 93.6 GB3215tok/sEstimated
Quant: Q8_0Context: 8,192VRAM: 14.4 GBHeadroom: 81.6 GBollama run qwen3:8b137tok/sEstimated
ollama run qwen3:8bQuant: Q8_0Context: 8,192VRAM: 6.9 GBHeadroom: 89.1 GBollama run llama3.2:3b365tok/sEstimated
ollama run llama3.2:3bQuant: Q4_K_MContext: 8,192VRAM: 3.6 GBHeadroom: 92.4 GB1135tok/sEstimated
Quant: Q4_K_MContext: 8,192VRAM: 11.1 GBHeadroom: 84.9 GBollama run dolphin3:8b241tok/sEstimated
ollama run dolphin3:8bQuant: Q4_K_MContext: 2,048VRAM: 2.6 GBHeadroom: 93.4 GB1754tok/sEstimated
Quant: Q4_K_MContext: 8,192VRAM: 4.0 GBHeadroom: 92.0 GB965tok/sEstimated
Quant: Q5_K_MContext: 8,192VRAM: 10.7 GBHeadroom: 85.3 GBollama run mistral:7b242tok/sEstimated
ollama run mistral:7bQuant: Q4_K_MContext: 8,192VRAM: 18.7 GBHeadroom: 77.3 GB804tok/sEstimated
Quant: Q8_0Context: 8,192VRAM: 16.6 GBHeadroom: 79.4 GBollama run gemma2:9b122tok/sEstimated
ollama run gemma2:9bQuant: Q4_K_MContext: 4,096VRAM: 7.6 GBHeadroom: 88.4 GB276tok/sEstimated
Quant: Q4_K_MContext: 8,192VRAM: 4.6 GBHeadroom: 91.4 GBollama run alibayram/kumru:latest804tok/sEstimated
ollama run alibayram/kumru:latestRuns with tradeoffs12 models
Tight VRAM, partial CPU offload, or context-limited.
Quant: Q4_K_MContext: 2,048VRAM: 172.0 GBHeadroom: 0.8 GB- • Partial CPU offload: ~44% of layers run on CPU
- • CPU is the bottleneck — upgrading RAM bandwidth helps more than VRAM here
29tok/sEstimated
- • Partial CPU offload: ~44% of layers run on CPU
- • CPU is the bottleneck — upgrading RAM bandwidth helps more than VRAM here
Quant: Q4_K_MContext: 8,192VRAM: 160.5 GBHeadroom: 12.3 GB- • Partial CPU offload: ~40% of layers run on CPU
- • CPU is the bottleneck — upgrading RAM bandwidth helps more than VRAM here
5tok/sEstimated
- • Partial CPU offload: ~40% of layers run on CPU
- • CPU is the bottleneck — upgrading RAM bandwidth helps more than VRAM here
Quant: Q4_K_MContext: 2,048VRAM: 172.0 GBHeadroom: 0.8 GB- • Partial CPU offload: ~44% of layers run on CPU
- • CPU is the bottleneck — upgrading RAM bandwidth helps more than VRAM here
29tok/sEstimated
- • Partial CPU offload: ~44% of layers run on CPU
- • CPU is the bottleneck — upgrading RAM bandwidth helps more than VRAM here
Quant: AWQ-INT4Context: 8,192VRAM: 159.9 GBHeadroom: 12.9 GB- • Partial CPU offload: ~40% of layers run on CPU
- • CPU is the bottleneck — upgrading RAM bandwidth helps more than VRAM here
25tok/sEstimated
- • Partial CPU offload: ~40% of layers run on CPU
- • CPU is the bottleneck — upgrading RAM bandwidth helps more than VRAM here
Quant: Q4_K_MContext: 2,048VRAM: 167.6 GBHeadroom: 5.2 GB- • Partial CPU offload: ~43% of layers run on CPU
- • CPU is the bottleneck — upgrading RAM bandwidth helps more than VRAM here
3tok/sEstimated
- • Partial CPU offload: ~43% of layers run on CPU
- • CPU is the bottleneck — upgrading RAM bandwidth helps more than VRAM here
Quant: Q4_K_MContext: 8,192VRAM: 146.6 GBHeadroom: 26.2 GB- • Partial CPU offload: ~34% of layers run on CPU
- • CPU is the bottleneck — upgrading RAM bandwidth helps more than VRAM here
20tok/sEstimated
- • Partial CPU offload: ~34% of layers run on CPU
- • CPU is the bottleneck — upgrading RAM bandwidth helps more than VRAM here
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:123bWhat 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: 9 new comfortable, 14 new tradeoff
- • Gemma 3 270M
- • SmolLM2 135M Instruct
- • SmolLM2 360M Instruct
- • VBART Large (Turkish Summarization)
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: 14 new comfortable
- • Gemma 3 270M
- • SmolLM2 135M Instruct
- • Mixtral 8x22B Instruct
- • WizardLM-2 8x22B
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: 23 new comfortable
- • Qwen 3 235B-A22B
- • GLM-5
- • Gemma 3 270M
- • SmolLM2 135M 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.