What can NVIDIA GeForce RTX 5090 Mobile run for reasoning?
Build: NVIDIA GeForce RTX 5090 Mobile + — + 32 GB RAM (windows)
Runs comfortably81 models
Ranked by fit for reasoning use case + predicted speed. Click a row for VRAM breakdown.
Quant: Q4_K_MContext: 8,192VRAM: 11.0 GBHeadroom: 13.0 GB128tok/sEstimated
Quant: Q4_K_MContext: 8,192VRAM: 11.0 GBHeadroom: 13.0 GBollama run RefinedNeuro/RN_TR_R1:latest128tok/sEstimated
ollama run RefinedNeuro/RN_TR_R1:latestQuant: Q4_K_MContext: 8,192VRAM: 10.7 GBHeadroom: 13.3 GB128tok/sEstimated
Quant: Q8_0Context: 8,192VRAM: 13.8 GBHeadroom: 10.2 GBollama run deepseek-r1:7b83tok/sEstimated
ollama run deepseek-r1:7bQuant: Q4_K_MContext: 8,192VRAM: 17.6 GBHeadroom: 6.4 GBollama run phi4-reasoning:14b73tok/sEstimated
ollama run phi4-reasoning:14bQuant: Q4_K_MContext: 8,192VRAM: 17.6 GBHeadroom: 6.4 GBollama run deepseek-r1:14b73tok/sEstimated
ollama run deepseek-r1:14bQuant: Q4_K_MContext: 8,192VRAM: 19.8 GBHeadroom: 4.2 GB426tok/sEstimated
Quant: Q4_K_MContext: 2,048VRAM: 19.5 GBHeadroom: 4.5 GB43tok/sEstimated
Quant: Q4_K_MContext: 8,192VRAM: 17.6 GBHeadroom: 6.4 GBollama run phi4:14b73tok/sEstimated
ollama run phi4:14bQuant: Q4_K_MContext: 8,192VRAM: 11.0 GBHeadroom: 13.0 GBollama run RefinedNeuro/RN_TR_R2:latest128tok/sEstimated
ollama run RefinedNeuro/RN_TR_R2:latestQuant: Q4_K_MContext: 8,192VRAM: 9.9 GBHeadroom: 14.1 GB146tok/sEstimated
Quant: Q4_K_MContext: 4,096VRAM: 8.2 GBHeadroom: 15.8 GB146tok/sEstimated
Runs with tradeoffs32 models
Tight VRAM, partial CPU offload, or context-limited.
Quant: Q4_K_MContext: 2,048VRAM: 23.6 GBHeadroom: 0.4 GB- • Tight VRAM fit — only 0.4 GB headroom left for context growth
33tok/sEstimated
- • Tight VRAM fit — only 0.4 GB headroom left for context growth
Quant: Q4_K_MContext: 8,192VRAM: 37.8 GBHeadroom: 5.4 GB- • Partial CPU offload: ~36% of layers run on CPU
ollama run deepseek-r1:32b32tok/sEstimated
- • Partial CPU offload: ~36% of layers run on CPU
ollama run deepseek-r1:32bQuant: Q4_K_MContext: 8,192VRAM: 37.8 GBHeadroom: 5.4 GB- • Partial CPU offload: ~36% of layers run on CPU
ollama run qwq:32b32tok/sEstimated
- • Partial CPU offload: ~36% of layers run on CPU
ollama run qwq:32bQuant: AWQ-INT4Context: 8,192VRAM: 37.8 GBHeadroom: 5.4 GB- • Partial CPU offload: ~36% of layers run on CPU
19tok/sEstimated
- • Partial CPU offload: ~36% of layers run on CPU
Quant: AWQ-INT4Context: 8,192VRAM: 37.8 GBHeadroom: 5.4 GB- • Partial CPU offload: ~36% of layers run on CPU
19tok/sEstimated
- • Partial CPU offload: ~36% of layers run on CPU
Quant: AWQ-INT4Context: 8,192VRAM: 37.8 GBHeadroom: 5.4 GB- • Partial CPU offload: ~36% of layers run on CPU
19tok/sEstimated
- • Partial CPU offload: ~36% of layers run on CPU
Quant: Q4_K_MContext: 8,192VRAM: 35.7 GBHeadroom: 7.5 GB- • Partial CPU offload: ~33% of layers run on CPU
ollama run nemotron3:nano34tok/sEstimated
- • Partial CPU offload: ~33% of layers run on CPU
ollama run nemotron3:nanoQuant: AWQ-INT4Context: 2,048VRAM: 37.3 GBHeadroom: 5.9 GB- • Partial CPU offload: ~36% of layers run on CPU
13tok/sEstimated
- • Partial CPU offload: ~36% of layers run on CPU
What if you upgraded?
Hypothetical scenarios. We re-ran the compatibility engine for each.
+32 GB system RAM
Check the current price
Adds 32 GB to your CPU-offload working set. Helps when models don't quite fit in VRAM.
Unlocks: 49 new comfortable, 48 new tradeoff
- • Qwen 3 0.6B
- • Qwen 3 1.7B
- • Llama 3.2 3B Instruct
- • Gemma 3 270M
Upgrade to NVIDIA GeForce RTX 5090
Launch MSRP $1,999 (2025). Check the current price.
32 GB VRAM (vs your 24 GB) plus a bandwidth jump from ~? GB/s to ~1792 GB/s.
Unlocks: 73 new comfortable
- • Qwen 3 0.6B
- • Qwen 3 30B-A3B
- • Qwen 2.5 Coder 32B Instruct
- • Qwen 3 32B
Add a second NVIDIA GeForce RTX 5090 Mobile
Check the current price
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: 81 new comfortable
- • Qwen 3 0.6B
- • Qwen 3 30B-A3B
- • Qwen 2.5 Coder 32B Instruct
- • Qwen 3 32B
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 (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.
—
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.
How to read these numbers
Want a specific benchmark we don't have? Email Contact support and we'll prioritize it.