Can I Run OLMo 2 on RTX 5090 Desktop (32 GB VRAM, 64 GB RAM)?

Written by Jakub Rusinowski · Last updated November 26, 2024

Yes — comfortably

Yes, comfortably — OLMo 2 13B Instruct at Q8_0 needs about 22.1 GB of the 32 GB usable on RTX 5090 Desktop (32 GB VRAM, 64 GB RAM), leaving ~9.9 GB spare and running at ~64.2 tok/s (estimated), with room for about 4,096 tokens of context.

Confidence: high · Recommended quantization: Q8_0 · Estimated speed: ~64.2 tok/s

RTX 5090 Desktop (32 GB VRAM, 64 GB RAM) — what it gives a model

Usable memory for models32 GB
Memory bandwidth1792 GB/s
Form factorDesktop
Operating systemWindows or Linux
Memory upgradeableYes

OLMo 2 on RTX 5090 Desktop (32 GB VRAM, 64 GB RAM): memory by quantization

QuantMemory neededFits 32 GB?Max contextEst. speedDownload
F1634.9 GB✗ No27.4 GB
Q8_022.1 GB✓ Yes4K~64.2 tok/s14.6 GB
Q6_K18.7 GB✓ Yes4K~76.3 tok/s11.2 GB
Q5_K_M17.2 GB✓ Yes4K~83.6 tok/s9.7 GB
Q4_K_M15.8 GB✓ Yes4K~91.8 tok/s8.3 GB
Q3_K_M13.4 GB✓ Yes4K~110 tok/s5.8 GB
Q2_K12 GB✓ Yes4K~123.6 tok/s4.5 GB

Which OLMo 2 sizes fit

VariantNeeds at Q4_K_MFits?Est. speed
OLMo 2 13B Instruct15.8 GB✓ Fits~91.8 tok/s
OLMo 2 7B Instruct9.5 GB✓ Fits~140.4 tok/s

What to watch out for

RTX 5090 desktop limitations

Recommended setup

Ollama or llama.cpp (CUDA/ROCm) — vLLM if you need concurrent serving

How these numbers are calculated

FAQ

Can I run OLMo 2 on RTX 5090 Desktop (32 GB VRAM, 64 GB RAM)?

Yes, comfortably — OLMo 2 13B Instruct at Q8_0 needs about 22.1 GB of the 32 GB usable on RTX 5090 Desktop (32 GB VRAM, 64 GB RAM), leaving ~9.9 GB spare and running at ~64.2 tok/s (estimated), with room for about 4,096 tokens of context.

Which quantization of OLMo 2 should I use on RTX 5090 Desktop (32 GB VRAM, 64 GB RAM)?

Q8_0 — it needs about 22.1 GB of the 32 GB available, downloads as roughly 14.6 GB, and runs at an estimated 64.2 tokens/sec with up to 4K of context.

What limits OLMo 2 on RTX 5090 Desktop (32 GB VRAM, 64 GB RAM)?

Nothing binding — the model fits with headroom and generates at a usable speed on this hardware.

Which runtime should I use?

Ollama or llama.cpp (CUDA/ROCm) — vLLM if you need concurrent serving

Other Computers

Other Models on RTX 5090 Desktop (32 GB VRAM, 64 GB RAM)

OLMo 2 on GPUs

What This Model Is Good At

Model & Tools

← Can I Run It? | OLMo 2 model page | Check your hardware