What can NVIDIA GeForce RTX 4090 Mobile run for chat?
Build: NVIDIA GeForce RTX 4090 Mobile + — + 32 GB RAM (windows)
Runs comfortably92 models
Ranked by fit for chat use case + predicted speed. Click a row for VRAM breakdown.
Quant: Q4_K_MContext: 8,192VRAM: 2.4 GBHeadroom: 13.6 GB1705tok/sEstimated
Quant: Q4_K_MContext: 8,192VRAM: 10.8 GBHeadroom: 5.2 GBollama run qwen3:8b128tok/sEstimated
ollama run qwen3:8bQuant: Q4_K_MContext: 8,192VRAM: 3.6 GBHeadroom: 12.4 GB602tok/sEstimated
Quant: Q8_0Context: 8,192VRAM: 6.9 GBHeadroom: 9.1 GBollama run llama3.2:3b194tok/sEstimated
ollama run llama3.2:3bQuant: Q4_K_MContext: 2,048VRAM: 2.6 GBHeadroom: 13.4 GB930tok/sEstimated
Quant: Q4_K_MContext: 8,192VRAM: 4.0 GBHeadroom: 12.0 GB511tok/sEstimated
Quant: Q5_K_MContext: 8,192VRAM: 10.7 GBHeadroom: 5.3 GBollama run mistral:7b128tok/sEstimated
ollama run mistral:7bQuant: Q4_K_MContext: 4,096VRAM: 7.6 GBHeadroom: 8.4 GB146tok/sEstimated
Quant: Q4_K_MContext: 8,192VRAM: 4.6 GBHeadroom: 11.4 GBollama run alibayram/kumru:latest426tok/sEstimated
ollama run alibayram/kumru:latestQuant: Q4_K_MContext: 8,192VRAM: 10.2 GBHeadroom: 5.8 GBollama run RefinedNeuro/Turkcell-LLM-7b-v1:latest138tok/sEstimated
ollama run RefinedNeuro/Turkcell-LLM-7b-v1:latestQuant: Q4_0Context: 8,192VRAM: 9.7 GBHeadroom: 6.3 GBollama run brooqs/mistral-turkish-v2:latest152tok/sEstimated
ollama run brooqs/mistral-turkish-v2:latestQuant: Q5_K_MContext: 8,192VRAM: 10.8 GBHeadroom: 5.2 GBollama run koezgen/malhajar-mistral-tur7b:latest125tok/sEstimated
ollama run koezgen/malhajar-mistral-tur7b:latestRuns with tradeoffs62 models
Tight VRAM, partial CPU offload, or context-limited.
Quant: Q4_K_MContext: 2,048VRAM: 12.8 GBHeadroom: 3.2 GB- • Tight VRAM fit — only 3.2 GB headroom left for context growth
426tok/sEstimated
- • Tight VRAM fit — only 3.2 GB headroom left for context growth
Quant: Q4_K_MContext: 8,192VRAM: 12.4 GBHeadroom: 3.6 GB- • Tight VRAM fit — only 3.6 GB headroom left for context growth
ollama run gemma2:9b114tok/sEstimated
- • Tight VRAM fit — only 3.6 GB headroom left for context growth
ollama run gemma2:9bQuant: Q4_K_MContext: 8,192VRAM: 15.7 GBHeadroom: 0.3 GB- • Tight VRAM fit — only 0.3 GB headroom left for context growth
ollama run mistral-nemo:12b85tok/sEstimated
- • Tight VRAM fit — only 0.3 GB headroom left for context growth
ollama run mistral-nemo:12bQuant: 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: 4,096VRAM: 12.4 GBHeadroom: 3.6 GB- • Tight VRAM fit — only 3.6 GB headroom left for context growth
85tok/sEstimated
- • Tight VRAM fit — only 3.6 GB headroom left for context growth
Quant: Q4_K_MContext: 2,048VRAM: 12.4 GBHeadroom: 3.6 GB- • Tight VRAM fit — only 3.6 GB headroom left for context growth
ollama run qwen3:14b73tok/sEstimated
- • Tight VRAM fit — only 3.6 GB headroom left for context growth
ollama run qwen3:14bQuant: Q4_K_MContext: 8,192VRAM: 28.5 GBHeadroom: 6.7 GB- • Partial CPU offload: ~44% of layers run on CPU
ollama run mistral-small:24b43tok/sEstimated
- • Partial CPU offload: ~44% of layers run on CPU
ollama run mistral-small:24bQuant: Q4_K_MContext: 8,192VRAM: 28.5 GBHeadroom: 6.7 GB- • Partial CPU offload: ~44% of layers run on CPU
43tok/sEstimated
- • Partial CPU offload: ~44% 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: 5 new comfortable, 78 new tradeoff
- • Gemma 3 270M
- • SmolLM2 135M Instruct
- • SmolLM2 360M Instruct
- • VBART Large (Turkish Summarization)
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: 24 new comfortable
- • Qwen 3 14B
- • Gemma 3 270M
- • Phi-4 14B
- • Phi-4 Reasoning 14B
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: 55 new comfortable
- • Qwen 3 30B-A3B
- • Qwen 2.5 Coder 32B Instruct
- • Qwen 3 32B
- • Gemma 4 31B Dense
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.