Rent a GPU

Can the NVIDIA RTX 5090 run gpt-oss 20B?

RTX 5090 × gpt-oss 20B8K context
YesRuns fully on the GPU
Memory at Q8_023 GB of 32 GB
Weights 22.2 GBKV cache 0.2 GBRuntime 0.6 GB
QuantQ8_0Near-lossless
Speed~281tokens per second
Max context128Kthe model's full window
  1. FP16
  2. Q8_0
  3. Q6_K
  4. Q5_K_M
  5. Q4_K_M
  6. Q3_K_M
  7. Q2_K

Yes. The NVIDIA RTX 5090 can run gpt-oss 20B fully in VRAM at Q8_0 (near-lossless), using about 23 GB of the 32 GB available, at roughly 281 tokens/second.

Try other context lengths

Run it with Ollama

With Ollama installed, one command downloads and starts gpt-oss 20B:

ollama run gpt-oss:20b

Ollama's default download is Q4_K_M (about 13.5 GB here). You have room for Q8_0, which is near-lossless: pick that GGUF in LM Studio or from Hugging Face.

New to this? Step-by-step setup for the RTX 5090

Run it in the cloud

No NVIDIA RTX 5090? Run gpt-oss 20B in the cloud.

Rent a cloud GPU by the hour. No upfront cost, stop any time.

Rent a GPU on RunPodRent a GPU on Vast.ai

Memory needed by quantization

At 8,192 tokens of context. The black line marks the 32 GB the NVIDIA RTX 5090 can use.

QuantQualityMemoryFits?Speed
FP16Full quality42.6 GBToo big—
Q8_0Near-lossless23 GBFits~281 tok/s
Q6_KExcellent17.9 GBFits~364 tok/s
Q5_K_MVery good15.7 GBFits~420 tok/s
Q4_K_MGood, most popular13.5 GBFits~493 tok/s
Q3_K_MNoticeably degraded11 GBFits~611 tok/s
Q2_KHeavily degraded8.6 GBFits~796 tok/s

Measured speed from real RTX 5090 owners

Tokens per second that people measured on their own NVIDIA RTX 5090, next to our estimate.

No one has measured gpt-oss 20B on the NVIDIA RTX 5090 yet. The speeds above are estimates. Run the benchmark and yours becomes the first real number on this page.

Have an RTX 5090? Add your real speed

One command times gpt-oss 20B in your own Ollama, shows you exactly what it would send, and asks before sending anything. No sign-up, no personal data.

macOS and Linux

curl -fsSL https://gpufit.dev/bench.sh | sh -s -- gpt-oss:20b

Windows (PowerShell)

$env:GPUFIT_MODEL="gpt-oss:20b"; irm https://gpufit.dev/bench.ps1 | iex

How the benchmark works

GPUs that run gpt-oss 20B comfortably

Models that run well on the NVIDIA RTX 5090

Frequently asked questions

Can NVIDIA RTX 5090 run gpt-oss 20B?

Yes. The NVIDIA RTX 5090 can run gpt-oss 20B fully in VRAM at Q8_0 (near-lossless), using about 23 GB of the 32 GB available, at roughly 281 tokens/second.

How much VRAM does gpt-oss 20B need?

About 13.5 GB at Q4_K_M with 8,192 tokens of context, and about 42.6 GB at full FP16 precision.

How fast is gpt-oss 20B on the NVIDIA RTX 5090?

Roughly 281 tokens per second at Q8_0, estimated from the NVIDIA RTX 5090's 1792 GB/s memory bandwidth.