What can NVIDIA GeForce RTX 4090 Mobile run for vision?
Build: NVIDIA GeForce RTX 4090 Mobile + — + 32 GB RAM (windows)
Runs comfortably14 models
Ranked by fit for vision use case + predicted speed. Click a row for VRAM breakdown.
Quant: Q8_0Context: 8,192VRAM: 8.4 GBHeadroom: 7.6 GBollama run gemma4:e4b145tok/sEstimated
ollama run gemma4:e4bQuant: Q8_0Context: 8,192VRAM: 8.4 GBHeadroom: 7.6 GBollama run gemma3:4b145tok/sEstimated
ollama run gemma3:4bQuant: Q8_0Context: 8,192VRAM: 5.1 GBHeadroom: 10.9 GBollama run gemma4:e2b291tok/sEstimated
ollama run gemma4:e2bQuant: Q4_K_MContext: 8,192VRAM: 6.5 GBHeadroom: 9.5 GB244tok/sEstimated
Quant: Q4_K_MContext: 8,192VRAM: 11.1 GBHeadroom: 4.9 GB128tok/sEstimated
Quant: Q4_K_MContext: 8,192VRAM: 9.9 GBHeadroom: 6.1 GB146tok/sEstimated
Quant: Q4_K_MContext: 8,192VRAM: 11.1 GBHeadroom: 4.9 GB128tok/sEstimated
Quant: Q4_K_MContext: 2,048VRAM: 3.3 GBHeadroom: 12.7 GB538tok/sEstimated
Quant: Q4_K_MContext: 8,192VRAM: 10.1 GBHeadroom: 5.9 GB146tok/sEstimated
Quant: Q4_K_MContext: 8,192VRAM: 10.0 GBHeadroom: 6.0 GB146tok/sEstimated
Quant: Q4_K_MContext: 8,192VRAM: 10.0 GBHeadroom: 6.0 GB146tok/sEstimated
Quant: Q4_K_MContext: 4,096VRAM: 9.3 GBHeadroom: 6.7 GB128tok/sEstimated
Runs with tradeoffs14 models
Tight VRAM, partial CPU offload, or context-limited.
Quant: Q4_K_MContext: 8,192VRAM: 15.6 GBHeadroom: 0.4 GB- • Tight VRAM fit — only 0.4 GB headroom left for context growth
ollama run llama3.2-vision:11b93tok/sEstimated
- • Tight VRAM fit — only 0.4 GB headroom left for context growth
ollama run llama3.2-vision:11bQuant: Q4_K_MContext: 8,192VRAM: 14.1 GBHeadroom: 1.9 GB- • Tight VRAM fit — only 1.9 GB headroom left for context growth
93tok/sEstimated
- • Tight VRAM fit — only 1.9 GB headroom left for context growth
Quant: Q4_K_MContext: 8,192VRAM: 15.5 GBHeadroom: 0.5 GB- • Tight VRAM fit — only 0.5 GB headroom left for context growth
ollama run gemma3:12b85tok/sEstimated
- • Tight VRAM fit — only 0.5 GB headroom left for context growth
ollama run gemma3:12bQuant: Q4_K_MContext: 8,192VRAM: 15.2 GBHeadroom: 0.8 GB- • Tight VRAM fit — only 0.8 GB headroom left for context growth
ollama run pixtral:12b85tok/sEstimated
- • Tight VRAM fit — only 0.8 GB headroom left for context growth
ollama run pixtral:12bQuant: Q4_K_MContext: 2,048VRAM: 12.5 GBHeadroom: 3.5 GB- • Tight VRAM fit — only 3.5 GB headroom left for context growth
74tok/sEstimated
- • Tight VRAM fit — only 3.5 GB headroom left for context growth
Quant: Q4_K_MContext: 2,048VRAM: 13.0 GBHeadroom: 3.0 GB- • Tight VRAM fit — only 3.0 GB headroom left for context growth
73tok/sEstimated
- • Tight VRAM fit — only 3.0 GB headroom left for context growth
Quant: GGUF_UNKNOWNContext: 8,192VRAM: 12.7 GBHeadroom: 3.3 GB- • Tight VRAM fit — only 3.3 GB headroom left for context growth
ollama run alibayram/Trendyol-LLM-Asure-12B:latest52tok/sEstimated
- • Tight VRAM fit — only 3.3 GB headroom left for context growth
ollama run alibayram/Trendyol-LLM-Asure-12B:latestQuant: Q4_K_MContext: 8,192VRAM: 31.6 GBHeadroom: 3.6 GB- • Partial CPU offload: ~49% of layers run on CPU
ollama run gemma4:26b-moe39tok/sEstimated
- • Partial CPU offload: ~49% of layers run on CPU
ollama run gemma4:26b-moeWhat 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: 83 new comfortable, 78 new tradeoff
- • Qwen 3 0.6B
- • Llama 3.1 8B Instruct
- • Qwen 3 8B
- • Qwen 3 1.7B
Upgrade to NVIDIA RTX 2080 Ti 22GB (China-mod)
Check the current price
22 GB VRAM (vs your 16 GB) plus a bandwidth jump from ~? GB/s to ~616 GB/s.
Unlocks: 102 new comfortable
- • Qwen 3 0.6B
- • Llama 3.1 8B Instruct
- • Qwen 3 8B
- • Qwen 3 1.7B
Add a second NVIDIA GeForce RTX 4090 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: 133 new comfortable
- • Qwen 3 0.6B
- • Llama 3.1 8B Instruct
- • Qwen 3 30B-A3B
- • Qwen 2.5 Coder 32B 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 (16 GB) + 60% of system RAM (19 GB) combined.
—
Even with CPU offload, needs more memory than your VRAM (16 GB) + 60% of system RAM (19 GB) combined.
Even with CPU offload, needs more memory than your VRAM (16 GB) + 60% of system RAM (19 GB) combined.
—
Even with CPU offload, needs more memory than your VRAM (16 GB) + 60% of system RAM (19 GB) combined.
Even with CPU offload, needs more memory than your VRAM (16 GB) + 60% of system RAM (19 GB) combined.
—
Even with CPU offload, needs more memory than your VRAM (16 GB) + 60% of system RAM (19 GB) combined.
Even with CPU offload, needs more memory than your VRAM (16 GB) + 60% of system RAM (19 GB) combined.
—
Even with CPU offload, needs more memory than your VRAM (16 GB) + 60% of system RAM (19 GB) combined.
Even with CPU offload, needs more memory than your VRAM (16 GB) + 60% of system RAM (19 GB) combined.
—
Even with CPU offload, needs more memory than your VRAM (16 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.