Can the NVIDIA RTX 4060 run gpt-oss 120B?
- FP16
- Q8_0
- Q6_K
- Q5_K_M
- Q4_K_M
- Q3_K_M
- Q2_K
No. Even at Q4_K_M, gpt-oss 120B needs about 71.7 GB, but the NVIDIA RTX 4060 has 8 GB usable. You could offload some layers to system RAM, but it will be very slow.
Run it on a rented GPU
On a cloud GPU with enough memory, the same command you'd use locally works:
ollama run gpt-oss:120bAt Q4_K_M it needs about 71.7 GB, so pick a GPU with at least 72 GB.
New to this? Step-by-step setup for the RTX 4060
Run it in the cloud
Too big for the NVIDIA RTX 4060? Run gpt-oss 120B on a rented GPU instead.
Rent a cloud GPU by the hour. No upfront cost, stop any time. Not sure whether to rent or buy? Compare the cost.
Memory needed by quantization
At 8,192 tokens of context. The black line marks the 8 GB the NVIDIA RTX 4060 can use.
| Quant | Quality | Memory | Fits? | Speed | |
|---|---|---|---|---|---|
| FP16 | Full quality | 234.5 GB | Too big | — | |
| Q8_0 | Near-lossless | 125 GB | Too big | — | |
| Q6_K | Excellent | 96.7 GB | Too big | — | |
| Q5_K_M | Very good | 84 GB | Too big | — | |
| Q4_K_M | Good, most popular | 71.7 GB | Too big | — | |
| Q3_K_M | Noticeably degraded | 58 GB | Too big | — | |
| Q2_K | Heavily degraded | 44.7 GB | Too big | — |
Measured speed from real RTX 4060 owners
Tokens per second that people measured on their own NVIDIA RTX 4060, next to our estimate.
No one has measured gpt-oss 120B on the NVIDIA RTX 4060 yet. The speeds above are estimates. Run the benchmark and yours becomes the first real number on this page.
Have an RTX 4060? 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:120bWindows (PowerShell)
$env:GPUFIT_MODEL="gpt-oss:120b"; irm https://gpufit.dev/bench.ps1 | iexGPUs that run gpt-oss 120B comfortably
Frequently asked questions
Can NVIDIA RTX 4060 run gpt-oss 120B?
No. Even at Q4_K_M, gpt-oss 120B needs about 71.7 GB, but the NVIDIA RTX 4060 has 8 GB usable. You could offload some layers to system RAM, but it will be very slow.
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 4060?
It does not fit in the NVIDIA RTX 4060's memory, so most layers would run from system RAM and generation would be very slow.