Build: NVIDIA GeForce RTX 5090 Mobile + — + 32 GB RAM (windows)
Ranked by fit for creative use case + predicted speed. Click a row for VRAM breakdown.
ollama run gemma4:e2bollama run gemma4:e4bollama run gemma3:4bollama run codegemma:7bollama run llama3.2:3bollama run phi3.5:3.8bollama run qwen3:4bTight VRAM, partial CPU offload, or context-limited.
ollama run hermes3:8bollama run gemma2:9bollama run dolphin-mistral:24bollama run gemma3:12bHypothetical 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: 7 new comfortable, 61 new tradeoff
~$2499
32 GB VRAM (vs your 24 GB) plus a bandwidth jump from ~? GB/s to ~1792 GB/s.
Unlocks: 35 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: 47 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 (24 GB) + 60% of system RAM (19 GB) combined.
Even with CPU offload, needs more memory than your VRAM (24 GB) + 60% of system RAM (19 GB) combined.
Even with CPU offload, needs more memory than your VRAM (24 GB) + 60% of system RAM (19 GB) combined.
Even with CPU offload, needs more memory than your VRAM (24 GB) + 60% of system RAM (19 GB) combined.
Even with CPU offload, needs more memory than your VRAM (24 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.