Can I Run GPT-OSS on RTX 3090 Desktop (24 GB VRAM, 64 GB RAM)?

Written by Jakub Rusinowski · Last updated August 15, 2026

Yes, but it is tight

Yes, but it is tight — GPT-OSS 20B at Q8_0 needs about 22.5 GB of the 24 GB usable on RTX 3090 Desktop (24 GB VRAM, 64 GB RAM), leaving only ~1.5 GB before the runtime starts swapping. Expect ~30.5 tok/s (estimated), with room for about 32,768 tokens of context.

Confidence: medium · Recommended quantization: Q8_0 · Estimated speed: ~30.5 tok/s

RTX 3090 Desktop (24 GB VRAM, 64 GB RAM) — what it gives a model

Usable memory for models24 GB
Memory bandwidth936 GB/s
Form factorDesktop
Operating systemWindows or Linux
Memory upgradeableYes

GPT-OSS on RTX 3090 Desktop (24 GB VRAM, 64 GB RAM): memory by quantization

QuantMemory neededFits 24 GB?Max contextEst. speedDownload
F1641.2 GB✗ No40 GB
Q8_022.5 GB✓ Yes32K~30.5 tok/s21.3 GB
Q6_K17.6 GB✓ Yes128K~38.6 tok/s16.4 GB
Q5_K_M15.4 GB✓ Yes128K~44 tok/s14.2 GB
Q4_K_M13.3 GB✓ Yes128K~50.7 tok/s12.1 GB
Q3_K_M9.7 GB✓ Yes128K~68.1 tok/s8.5 GB
Q2_K7.8 GB✓ Yes128K~84 tok/s6.6 GB

Which GPT-OSS sizes fit

VariantNeeds at Q4_K_MFits?Est. speed
GPT-oss 120B73.9 GB✗ Too large
GPT-OSS 20B13.3 GB✓ Fits~50.7 tok/s

What to watch out for

RTX 3090 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 GPT-OSS on RTX 3090 Desktop (24 GB VRAM, 64 GB RAM)?

Yes, but it is tight — GPT-OSS 20B at Q8_0 needs about 22.5 GB of the 24 GB usable on RTX 3090 Desktop (24 GB VRAM, 64 GB RAM), leaving only ~1.5 GB before the runtime starts swapping. Expect ~30.5 tok/s (estimated), with room for about 32,768 tokens of context.

Which quantization of GPT-OSS should I use on RTX 3090 Desktop (24 GB VRAM, 64 GB RAM)?

Q8_0 — it needs about 22.5 GB of the 24 GB available, downloads as roughly 21.3 GB, and runs at an estimated 30.5 tokens/sec with up to 32K of context.

What limits GPT-OSS on RTX 3090 Desktop (24 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 3090 Desktop (24 GB VRAM, 64 GB RAM)

GPT-OSS on GPUs

What This Model Is Good At

Model & Tools

← Can I Run It? | GPT-OSS model page | Check your hardware