Rent a GPU

Can the NVIDIA RTX 4090 run gpt-oss 20B?

RTX 4090 × gpt-oss 20B8K context
YesRuns fully on the GPU
Memory at Q8_023.2 GB of 24 GB
Weights 22.2 GBKV cache 0.4 GBRuntime 0.6 GB
QuantQ8_0Near-lossless
Memory23.2 GBof 24 GB usable
Speed~158tokens 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

Yes. The NVIDIA RTX 4090 can run gpt-oss 20B fully in VRAM at Q8_0 (near-lossless), using about 23.2 GB of the 24 GB available, at roughly 158 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 13.7 GB here). You have room for Q8_0, which is near-lossless: pick that GGUF in LM Studio or from Hugging Face.

Run it in the cloud

No NVIDIA RTX 4090? 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 24 GB the NVIDIA RTX 4090 can use.

QuantQualityMemoryFits?Speed
FP16Full quality42.8 GBToo big—
Q8_0Near-lossless23.2 GBFits~158 tok/s
Q6_KExcellent18.1 GBFits~205 tok/s
Q5_K_MVery good15.9 GBFits~236 tok/s
Q4_K_MGood, most popular13.7 GBFits~277 tok/s
Q3_K_MNoticeably degraded11.2 GBFits~344 tok/s
Q2_KHeavily degraded8.8 GBFits~448 tok/s

GPUs that run gpt-oss 20B comfortably

Models that run well on the NVIDIA RTX 4090

Frequently asked questions

Can NVIDIA RTX 4090 run gpt-oss 20B?

Yes. The NVIDIA RTX 4090 can run gpt-oss 20B fully in VRAM at Q8_0 (near-lossless), using about 23.2 GB of the 24 GB available, at roughly 158 tokens/second.

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 4090?

Roughly 158 tokens per second at Q8_0, estimated from the NVIDIA RTX 4090's 1008 GB/s memory bandwidth.