What can NVIDIA GeForce RTX 5090 run for long context?
Build: RTX 5090 + Ryzen 9 9950X + 64GB DDR5
Runs comfortably100 models
Ranked by fit for long context use case + predicted speed. Click a row for VRAM breakdown.
Quant: Q8_0Context: 8,192VRAM: 14.4 GBHeadroom: 17.6 GBTTFT: fastollama run qwen3:8b137tok/sEstimated
ollama run qwen3:8bQuant: Q8_0Context: 8,192VRAM: 10.8 GBHeadroom: 21.2 GBTTFT: fastollama run qwen2.5:7b157tok/sEstimated
ollama run qwen2.5:7bQuant: Q8_0Context: 8,192VRAM: 8.4 GBHeadroom: 23.6 GBTTFT: instantollama run gemma4:e4b274tok/sEstimated
ollama run gemma4:e4bQuant: Q8_0Context: 8,192VRAM: 8.0 GBHeadroom: 24.0 GBTTFT: instantollama run phi3.5:3.8b288tok/sEstimated
ollama run phi3.5:3.8bQuant: Q4_K_MContext: 8,192VRAM: 10.4 GBHeadroom: 21.6 GBTTFT: fast241tok/sEstimated
Quant: Q4_K_MContext: 8,192VRAM: 9.7 GBHeadroom: 22.3 GBTTFT: fast276tok/sEstimated
Quant: Q4_K_MContext: 8,192VRAM: 9.7 GBHeadroom: 22.3 GBTTFT: fast276tok/sEstimated
Quant: Q4_K_MContext: 8,192VRAM: 11.1 GBHeadroom: 20.9 GBTTFT: fast241tok/sEstimated
Quant: Q8_0Context: 8,192VRAM: 21.5 GBHeadroom: 10.5 GBTTFT: fastollama run mistral-nemo:12b91tok/sEstimated
ollama run mistral-nemo:12bQuant: Q8_0Context: 8,192VRAM: 24.6 GBHeadroom: 7.4 GBTTFT: fastollama run qwen3:14b78tok/sEstimated
ollama run qwen3:14bQuant: Q8_0Context: 8,192VRAM: 25.3 GBHeadroom: 6.7 GBTTFT: fastollama run qwen2.5:14b78tok/sEstimated
ollama run qwen2.5:14bQuant: FP16Context: 8,192VRAM: 19.8 GBHeadroom: 12.2 GBTTFT: fastollama run llama3.1:8b73tok/sEstimated
ollama run llama3.1:8bRuns with tradeoffs22 models
Tight VRAM, partial CPU offload, or context-limited.
Quant: Q4_K_MContext: 8,192VRAM: 29.8 GBHeadroom: 2.2 GBTTFT: noticeable- • Tight VRAM fit — only 2.2 GB headroom left for context growth
74tok/sEstimated
- • Tight VRAM fit — only 2.2 GB headroom left for context growth
Quant: Q4_K_MContext: 2,048VRAM: 28.2 GBHeadroom: 3.8 GBTTFT: noticeable- • Tight VRAM fit — only 3.8 GB headroom left for context growth
ollama run command-r:35b55tok/sEstimated
- • Tight VRAM fit — only 3.8 GB headroom left for context growth
ollama run command-r:35bQuant: Q4_K_MContext: 8,192VRAM: 59.3 GBHeadroom: 11.1 GBTTFT: fast- • Partial CPU offload: ~46% of layers run on CPU
- • CPU is the bottleneck — upgrading RAM bandwidth helps more than VRAM here
10tok/sEstimated
- • Partial CPU offload: ~46% of layers run on CPU
- • CPU is the bottleneck — upgrading RAM bandwidth helps more than VRAM here
Quant: Q4_K_MContext: 8,192VRAM: 28.5 GBHeadroom: 3.5 GBTTFT: fast- • Tight VRAM fit — only 3.5 GB headroom left for context growth
ollama run mistral-small:24b80tok/sEstimated
- • Tight VRAM fit — only 3.5 GB headroom left for context growth
ollama run mistral-small:24bQuant: Q4_K_MContext: 8,192VRAM: 28.5 GBHeadroom: 3.5 GBTTFT: fast- • Tight VRAM fit — only 3.5 GB headroom left for context growth
ollama run dolphin-mistral:24b80tok/sEstimated
- • Tight VRAM fit — only 3.5 GB headroom left for context growth
ollama run dolphin-mistral:24bQuant: Q4_K_MContext: 2,048VRAM: 52.6 GBHeadroom: 17.8 GBTTFT: noticeable- • Partial CPU offload: ~39% of layers run on CPU
- • CPU is the bottleneck — upgrading RAM bandwidth helps more than VRAM here
ollama run llama3.1:70b2tok/sEstimated
- • Partial CPU offload: ~39% of layers run on CPU
- • CPU is the bottleneck — upgrading RAM bandwidth helps more than VRAM here
ollama run llama3.1:70bQuant: Q4_K_MContext: 2,048VRAM: 52.6 GBHeadroom: 17.8 GBTTFT: noticeable- • Partial CPU offload: ~39% of layers run on CPU
- • CPU is the bottleneck — upgrading RAM bandwidth helps more than VRAM here
ollama run nemotron:70b2tok/sEstimated
- • Partial CPU offload: ~39% of layers run on CPU
- • CPU is the bottleneck — upgrading RAM bandwidth helps more than VRAM here
ollama run nemotron:70bQuant: Q4_K_MContext: 8,192VRAM: 31.6 GBHeadroom: 0.4 GBTTFT: noticeable- • Tight VRAM fit — only 0.4 GB headroom left for context growth
74tok/sEstimated
- • Tight VRAM fit — only 0.4 GB headroom left for context growth
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: 28 new comfortable, 25 new tradeoff
- • Qwen 3 0.6B
- • Qwen 3 1.7B
- • Gemma 3 270M
- • SmolLM2 135M Instruct
Upgrade to NVIDIA A100 40GB
Launch MSRP $11,000 (2020). Check the current price.
40 GB VRAM (vs your 32 GB) plus a bandwidth jump from ~1792 GB/s to ~? GB/s.
Unlocks: 34 new comfortable
- • Qwen 3 0.6B
- • Qwen 3 1.7B
- • Gemma 3 270M
- • Mistral Small 3 24B
Add a second NVIDIA GeForce RTX 5090
Launch MSRP $1,999 (2025). 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: 46 new comfortable
- • Qwen 3 0.6B
- • Llama 3.3 70B Instruct
- • DeepSeek R1 Distill Llama 70B
- • Qwen 3 1.7B
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 (32 GB) + 60% of system RAM (38 GB) combined.
—
Even with CPU offload, needs more memory than your VRAM (32 GB) + 60% of system RAM (38 GB) combined.
Even with CPU offload, needs more memory than your VRAM (32 GB) + 60% of system RAM (38 GB) combined.
—
Even with CPU offload, needs more memory than your VRAM (32 GB) + 60% of system RAM (38 GB) combined.
Even with CPU offload, needs more memory than your VRAM (32 GB) + 60% of system RAM (38 GB) combined.
—
Even with CPU offload, needs more memory than your VRAM (32 GB) + 60% of system RAM (38 GB) combined.
Even with CPU offload, needs more memory than your VRAM (32 GB) + 60% of system RAM (38 GB) combined.
—
Even with CPU offload, needs more memory than your VRAM (32 GB) + 60% of system RAM (38 GB) combined.
Even with CPU offload, needs more memory than your VRAM (32 GB) + 60% of system RAM (38 GB) combined.
—
Even with CPU offload, needs more memory than your VRAM (32 GB) + 60% of system RAM (38 GB) combined.
Not enough VRAM for these models? Rent a GPU by the hour
The models above need more memory than 32 GB VRAM + 64 GB system RAM. You can rent a GPU with enough VRAM by the hour to run one of them, or to test it before you buy hardware. For daily use, owning a card usually costs less over time.
RunPod
billed per GPU-hourHourly GPU pods, in community-cloud and secure-cloud tiers.
The two tiers run on different hosts and terms. Check which tier a pod is on before a long job.
Rent on RunPodVast.ai
billed per GPU-hourMarketplace of host-listed GPUs; price and reliability vary by host.
Host quality varies. Filter for verified hosts and check the host's reliability before a long run.
Rent on Vast.aiReferral links: RunLocalAI may earn a commission or account credits if you sign up and rent, at no extra cost to you. Hourly rates and which GPUs are listed change all the time, so check the provider's page before you start. Editorial opinions are independent of the referral relationship; see how we make money.
How to read these numbers
Want a specific benchmark we don't have? Email Contact support and we'll prioritize it.