Rent a GPU

Can the NVIDIA RTX PRO 6000 Blackwell run gpt-oss 120B?

RTX PRO 6000 Blackwell × gpt-oss 120B8K context
YesRuns fully on the GPU
Memory at Q5_K_M84 GB of 96 GB
Weights 83.1 GBKV cache 0.3 GBRuntime 0.6 GB
QuantQ5_K_MVery good
Speed~296tokens 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 PRO 6000 Blackwell can run gpt-oss 120B fully in VRAM at Q5_K_M (very good), using about 84 GB of the 96 GB available, at roughly 296 tokens/second.

Try other context lengths

Run it with Ollama

With Ollama installed, one command downloads and starts gpt-oss 120B:

ollama run gpt-oss:120b

Ollama's default download is Q4_K_M (about 71.7 GB here). You have room for Q5_K_M, which is very good: pick that GGUF in LM Studio or from Hugging Face.

New to this? Step-by-step setup for the RTX PRO 6000 Blackwell

Run it in the cloud

No NVIDIA RTX PRO 6000 Blackwell? Run gpt-oss 120B 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 96 GB the NVIDIA RTX PRO 6000 Blackwell can use.

QuantQualityMemoryFits?Speed
FP16Full quality234.5 GBToo big—
Q8_0Near-lossless125 GBToo big—
Q6_KExcellent96.7 GBToo big—
Q5_K_MVery good84 GBFits~296 tok/s
Q4_K_MGood, most popular71.7 GBFits~348 tok/s
Q3_K_MNoticeably degraded58 GBFits~431 tok/s
Q2_KHeavily degraded44.7 GBFits~562 tok/s

Measured speed from real RTX PRO 6000 Blackwell owners

Tokens per second that people measured on their own NVIDIA RTX PRO 6000 Blackwell, next to our estimate.

No one has measured gpt-oss 120B on the NVIDIA RTX PRO 6000 Blackwell yet. The speeds above are estimates. Run the benchmark and yours becomes the first real number on this page.

Have an RTX PRO 6000 Blackwell? Add your real speed

One command times gpt-oss 120B 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:120b

Windows (PowerShell)

$env:GPUFIT_MODEL="gpt-oss:120b"; irm https://gpufit.dev/bench.ps1 | iex

How the benchmark works

GPUs that run gpt-oss 120B comfortably

Models that run well on the NVIDIA RTX PRO 6000 Blackwell

Frequently asked questions

Can NVIDIA RTX PRO 6000 Blackwell run gpt-oss 120B?

Yes. The NVIDIA RTX PRO 6000 Blackwell can run gpt-oss 120B fully in VRAM at Q5_K_M (very good), using about 84 GB of the 96 GB available, at roughly 296 tokens/second.

How much VRAM does gpt-oss 120B need?

About 71.7 GB at Q4_K_M with 8,192 tokens of context, and about 234.5 GB at full FP16 precision.

How fast is gpt-oss 120B on the NVIDIA RTX PRO 6000 Blackwell?

Roughly 296 tokens per second at Q5_K_M, estimated from the NVIDIA RTX PRO 6000 Blackwell's 1792 GB/s memory bandwidth.