Rent a GPU

Can the NVIDIA RTX 3060 12GB run gpt-oss 20B?

RTX 3060 12GB × gpt-oss 20B8K context
Yes, with heavy quantizationFits only at a low-quality quant
Memory at Q3_K_M11.2 GB of 12 GB
Weights 10.2 GBKV cache 0.4 GBRuntime 0.6 GB
QuantQ3_K_MNoticeably degraded
Memory11.2 GBof 12 GB usable
Speed~123tokens per second
  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 3060 12GB at Q3_K_M, which costs noticeable quality. Expect about 123 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 13.7 GB, more than the 12 GB available. Download the Q3_K_M GGUF instead (LM Studio lists quants per model), or try a smaller context length.

New to this? Step-by-step setup for the RTX 3060 12GB

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 12 GB the NVIDIA RTX 3060 12GB can use.

QuantQualityMemoryFits?Speed
FP16Full quality42.8 GBToo big—
Q8_0Near-lossless23.2 GBToo big—
Q6_KExcellent18.1 GBToo big—
Q5_K_MVery good15.9 GBToo big—
Q4_K_MGood, most popular13.7 GBToo big—
Q3_K_MNoticeably degraded11.2 GBFits~123 tok/s
Q2_KHeavily degraded8.8 GBFits~160 tok/s

GPUs that run gpt-oss 20B comfortably

Check NVIDIA RTX 4060 Ti 16GB prices

Models that run well on the NVIDIA RTX 3060 12GB

Frequently asked questions

Can NVIDIA RTX 3060 12GB run gpt-oss 20B?

Only just. gpt-oss 20B fits on the NVIDIA RTX 3060 12GB at Q3_K_M, which costs noticeable quality. Expect about 123 tokens/second. A card with more memory is a better experience.

How much VRAM does gpt-oss 20B need?

About 13.7 GB at Q4_K_M with 8,192 tokens of context, and about 42.8 GB at full FP16 precision.

How fast is gpt-oss 20B on the NVIDIA RTX 3060 12GB?

Roughly 123 tokens per second at Q3_K_M, estimated from the NVIDIA RTX 3060 12GB's 360 GB/s memory bandwidth.