Rent a GPU

Can the NVIDIA RTX 3080 10GB run gpt-oss 20B?

RTX 3080 10GB × gpt-oss 20B8K context
Yes, with heavy quantizationFits only at a low-quality quant
Memory at Q2_K8.6 GB of 10 GB
Weights 7.8 GBKV cache 0.2 GBRuntime 0.6 GB
QuantQ2_KHeavily degraded
Speed~338tokens per second
Max context61Ktokens that fit at Q2_K
  1. FP16
  2. Q8_0
  3. Q6_K
  4. Q5_K_M
  5. Q4_K_M
  6. Q3_K_M
  7. Q2_K

Only just. gpt-oss 20B fits on the NVIDIA RTX 3080 10GB at Q2_K, which costs noticeable quality. Expect about 338 tokens/second. A card with more memory is a better experience.

Try other context lengths

Run it with Ollama

Ollama's default gpt-oss:20b download is Q4_K_M, which needs about 13.5 GB, more than the 10 GB available. Download the Q2_K GGUF instead (LM Studio lists quants per model), or try a smaller context length.

New to this? Step-by-step setup for the RTX 3080 10GB

Run it in the cloud

Want full quality? Run gpt-oss 20B on a bigger rented GPU.

Rent a cloud GPU by the hour. No upfront cost, stop any time. Not sure whether to rent or buy? Compare the cost.

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 10 GB the NVIDIA RTX 3080 10GB can use.

QuantQualityMemoryFits?Speed
FP16Full quality42.6 GBToo big—
Q8_0Near-lossless23 GBToo big—
Q6_KExcellent17.9 GBToo big—
Q5_K_MVery good15.7 GBToo big—
Q4_K_MGood, most popular13.5 GBToo big—
Q3_K_MNoticeably degraded11 GBToo big—
Q2_KHeavily degraded8.6 GBFits~338 tok/s

Measured speed from real RTX 3080 10GB owners

Tokens per second that people measured on their own NVIDIA RTX 3080 10GB, next to our estimate.

No one has measured gpt-oss 20B on the NVIDIA RTX 3080 10GB yet. The speeds above are estimates. Run the benchmark and yours becomes the first real number on this page.

Have an RTX 3080 10GB? 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

Check RTX 4060 Ti 16GB prices

Models that run well on the NVIDIA RTX 3080 10GB

Frequently asked questions

Can NVIDIA RTX 3080 10GB run gpt-oss 20B?

Only just. gpt-oss 20B fits on the NVIDIA RTX 3080 10GB at Q2_K, which costs noticeable quality. Expect about 338 tokens/second. A card with more memory is a better experience.

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 3080 10GB?

Roughly 338 tokens per second at Q2_K, estimated from the NVIDIA RTX 3080 10GB's 760 GB/s memory bandwidth.