Build: NVIDIA GB200 NVL72 + — + 32 GB RAM (windows)
Ranked by fit for coding use case + predicted speed. Click a row for VRAM breakdown.
ollama run codegemma:7bollama run deepseek-coder-v2:16bollama run codestral:22bollama run qwen2.5-coder:32bollama run qwen3:30bollama run gemma4:31bollama run qwen3:32bollama run qwen2.5:32bollama run llama3.1:70bollama run llama3.3:70bollama run qwen3:14bollama run qwen2.5:14bHypothetical scenarios. We re-ran the compatibility engine for each.
~$80–150
Doubles your CPU-offload working set. Helps when models don't quite fit in VRAM.
Unlocks: 17 new comfortable
see current pricing
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: 17 new comfortable
Some links above are affiliate links. We may earn a commission at no extra cost to you. How we make money.
Need more memory than you have. Shown for orientation.
Even with CPU offload, needs more memory than your VRAM (13824 GB) + 60% of system RAM (19 GB) combined.
Even with CPU offload, needs more memory than your VRAM (13824 GB) + 60% of system RAM (19 GB) combined.
Even with CPU offload, needs more memory than your VRAM (13824 GB) + 60% of system RAM (19 GB) combined.
Want a specific benchmark we don't have? Email support@runlocalai.co and we'll prioritize it.