Build: NVIDIA RTX 4090 48GB (China-mod) + — + 32 GB RAM (windows)
Ranked by fit for long context use case + predicted speed. Click a row for VRAM breakdown.
ollama run phi3.5:3.8bollama run gemma4:e4bollama run qwen2.5:7bollama run qwen3:8bollama run mistral-nemo:12bollama run qwen3:14bTight VRAM, partial CPU offload, or context-limited.
ollama run nemotron3:nanoollama run qwen3:30bollama run gemma4:31bollama run qwen3:32bollama run qwen2.5:32bollama run llama3.1:70bollama run nemotron:70bollama run qwen2.5:72bHypothetical 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, 28 new tradeoff
see current pricing
80 GB VRAM (vs your 48 GB) plus a bandwidth jump from ~1008 GB/s to ~3350 GB/s.
Unlocks: 40 new comfortable
~$2400
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: 46 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 (48 GB) + 60% of system RAM (19 GB) combined.
Even with CPU offload, needs more memory than your VRAM (48 GB) + 60% of system RAM (19 GB) combined.
Even with CPU offload, needs more memory than your VRAM (48 GB) + 60% of system RAM (19 GB) combined.
Even with CPU offload, needs more memory than your VRAM (48 GB) + 60% of system RAM (19 GB) combined.
Even with CPU offload, needs more memory than your VRAM (48 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.